INDEX

Explanations

statements or questions related to actions or consequences

oai_token-act-pair · gpt-3.5-turbo

phrases that involve people discussing topics related to communities and social interactions

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

 Hass

-0.67

atl

-0.64

 Icelandic

-0.60

 Mous

-0.56

annis

-0.56

tsky

-0.55

tyard

-0.55

Bru

-0.55

Ruby

-0.54

uli

-0.54

POSITIVE LOGITS

azo

0.76

'>

0.73

',"

0.65

 automatically

0.64

morrow

0.64

Leaks

0.64

 damn

0.63

ulla

0.62

 gonna

0.61

etheless

0.60

Activations Density 0.667%

statements or questions related to actions or consequences

phrases that involve people discussing topics related to communities and social interactions

No Comments

No Known Activations