INDEX

Explanations

questions starting with 'If' and statements involving thoughts or opinions

oai_token-act-pair · gpt-3.5-turbo

conditional statements and hypotheses

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ģĸ

-0.76

illation

-0.72

peror

-0.69

apult

-0.65

drawn

-0.64

ngth

-0.64

isitions

-0.61

angering

-0.61

ptoms

-0.61

apan

-0.60

POSITIVE LOGITS

yes

1.27

so

1.12

 Nope

0.96

not

0.96

YES

0.92

it

0.85

 thats

0.83

Yes

0.82

Yes

0.82

NOT

0.82

Activations Density 0.163%

questions starting with 'If' and statements involving thoughts or opinions

conditional statements and hypotheses

No Comments

No Known Activations