INDEX

Explanations

phrases indicating future actions or events

oai_token-act-pair · gpt-3.5-turbo

occurrences of verbs signaling upcoming events or actions

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

pmwiki

-0.82

Avg

-0.76

 forgetting

-0.66

 supposed

-0.65

quickShipAvailable

-0.60

 gotta

-0.59

atto

-0.59

maxwell

-0.58

 Administ

-0.57

 Mint

-0.57

POSITIVE LOGITS

 tomorrow

0.96

ezvous

0.87

omething

0.83

 sometime

0.79

 someday

0.76

dress

0.73

aturday

0.72

uate

0.69

igate

0.69

morrow

0.69

Activations Density 0.321%

phrases indicating future actions or events

occurrences of verbs signaling upcoming events or actions

No Comments

No Known Activations