INDEX

Explanations

instances where a hypothetical situation could have been different if a specific action or decision had been taken

oai_token-act-pair · gpt-3.5-turbo

the phrase "could have" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

ocol

-0.60

bert

-0.59

 paycheck

-0.57

 hostage

-0.57

vich

-0.56

Mem

-0.56

pour

-0.56

 metro

-0.55

 doll

-0.54

Dud

-0.54

POSITIVE LOGITS

 been

0.94

ħĭ

0.90

 gotten

0.88

idon

0.84

ivably

0.84

 Been

0.78

been

0.75

¶ħ

0.75

Ïģ

0.74

 avoided

0.74

Activations Density 0.037%

instances where a hypothetical situation could have been different if a specific action or decision had been taken

the phrase "could have" in various contexts

No Comments

No Known Activations