INDEX

Explanations

phrases containing pronouns followed by "be" verbs

oai_token-act-pair · gpt-3.5-turbo

references to a specific individual, highlighting their actions and characteristics

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

DAY

-0.71

âĦ¢:

-0.69

Sao

-0.63

 Alas

-0.63

 è£ıè

-0.62

 Gund

-0.61

XI

-0.59

 Mehran

-0.59

prem

-0.57

Pad

-0.56

POSITIVE LOGITS

zbollah

1.29

 mathemat

0.96

'll

0.95

0.92

're

0.91

pherd

0.90

 incent

0.89

 definitely

0.87

ain

0.87

 really

0.87

Activations Density 0.284%

phrases containing pronouns followed by "be" verbs

references to a specific individual, highlighting their actions and characteristics

No Comments

No Known Activations