INDEX

Explanations

proper nouns or names of individuals

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "in."

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 incumb

-0.74

 innoc

-0.72

 includ

-0.65

username

-0.62

WER

-0.62

 stakeholders

-0.62

 lodged

-0.62

awei

-0.61

USB

-0.61

information

-0.61

POSITIVE LOGITS

 lieu

1.21

 conjunction

1.21

 accordance

1.05

ked

1.00

 favor

0.98

 spite

0.95

 relation

0.94

animate

0.94

 unison

0.94

clus

0.92

Activations Density 0.234%

proper nouns or names of individuals

occurrences of the word "in."

No Comments

No Known Activations