INDEX

Explanations

phrases with the word "definition."

oai_token-act-pair · gpt-3.5-turbo

the term "definition" as it relates to various concepts

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

orld

-0.76

pload

-0.75

 Pradesh

-0.72

ocamp

-0.70

olulu

-0.70

ili

-0.68

estern

-0.68

roph

-0.67

ieri

-0.67

 Nort

-0.65

POSITIVE LOGITS

inition

0.95

witz

0.85

 definitions

0.84

initions

0.82

 definition

0.81

 defines

0.79

lessly

0.77

idable

0.72

gence

0.71

 criteria

0.70

Activations Density 0.016%

phrases with the word "definition."

the term "definition" as it relates to various concepts

No Comments

No Known Activations