INDEX

Explanations

mentions of specific individuals and their actions or characteristics

oai_token-act-pair · gpt-3.5-turbo

conjunctions and words that indicate relationships or connections between ideas

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

issance

-0.81

ESA

-0.65

HM

-0.64

ruary

-0.63

ascript

-0.60

externalActionCode

-0.60

ĸļ

-0.59

 nomine

-0.58

lication

-0.58

ESE

-0.58

POSITIVE LOGITS

 chops

0.60

owl

0.56

 feat

0.55

fork

0.54

ĪĴ

0.54

Bone

0.54

 flakes

0.54

sect

0.54

 wheels

0.53

Ingredients

0.53

Activations Density 0.464%

mentions of specific individuals and their actions or characteristics

conjunctions and words that indicate relationships or connections between ideas

No Comments

No Known Activations