INDEX

Explanations

phrases related to proving or disproving statements or theories, particularly with a focus on scientific evidence or research

oai_token-act-pair · gpt-3.5-turbo

verbs and variations of the word "prove" or its derivatives

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 contrace

-0.90

irlf

-0.75

 ILCS

-0.74

oppy

-0.73

cair

-0.71

 Ches

-0.70

 peas

-0.68

ufact

-0.66

eston

-0.65

akra

-0.64

POSITIVE LOGITS

 dispro

0.79

 Grounds

0.76

tale

0.74

iary

0.73

ailable

0.73

grounds

0.71

 Evidence

0.71

 proving

0.70

 Presence

0.69

 untrue

0.68

Activations Density 0.065%

phrases related to proving or disproving statements or theories, particularly with a focus on scientific evidence or research

verbs and variations of the word "prove" or its derivatives

No Comments

No Known Activations