INDEX

Explanations

verbs in the past tense indicating the beginning or completion of actions

oai_token-act-pair · gpt-3.5-turbo

instances of significant actions or events leading to consequences

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

pires

-0.63

 Appears

-0.58

 successor

-0.58

 reminds

-0.55

HAS

-0.55

bara

-0.54

 assumes

-0.54

 Transparency

-0.54

 begs

-0.53

 Timeline

-0.52

POSITIVE LOGITS

 theirs

1.04

 respectively

0.93

their

0.93

 themselves

0.83

itored

0.75

}.

0.72

 apiece

0.71

ranged

0.68

abouts

0.67

'.

0.66

Activations Density 1.511%

verbs in the past tense indicating the beginning or completion of actions

instances of significant actions or events leading to consequences

No Comments

No Known Activations