INDEX

Explanations

statements indicating capability or action in the context of various scenarios

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "able."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Parents

-0.69

 Concern

-0.64

 Sins

-0.64

 Gone

-0.63

 Nose

-0.60

 Caval

-0.59

 Yose

-0.59

 Bots

-0.59

alien

-0.58

 Generation

-0.58

POSITIVE LOGITS

bodied

0.88

't

0.86

ioned

0.85

reys

0.83

Reviewer

0.80

untarily

0.78

 successfully

0.78

uate

0.72

uced

0.72

ittees

0.72

Activations Density 0.033%

statements indicating capability or action in the context of various scenarios

occurrences of the word "able."

No Comments

No Known Activations