INDEX

Explanations

adjectives describing a specific desired outcome or effect

oai_token-act-pair · gpt-3.5-turbo

terms related to achieving a desired outcome or effect

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

mans

-0.88

olic

-0.76

man

-0.75

rup

-0.74

hero

-0.74

raph

-0.74

ols

-0.74

sheet

-0.74

sheets

-0.73

pat

-0.70

POSITIVE LOGITS

igslist

0.94

atile

0.80

 fulfil

0.77

 outcomes

0.77

 Parenthood

0.75

 surprises

0.75

 destination

0.74

 outcome

0.73

 mosqu

0.71

 destinations

0.70

Activations Density 0.031%

adjectives describing a specific desired outcome or effect

terms related to achieving a desired outcome or effect

No Comments

No Known Activations