INDEX

Explanations

proper nouns or names of specific entities

oai_token-act-pair · gpt-3.5-turbo

the phrase "which" followed by various forms of information or descriptions

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

any

-0.69

cup

-0.63

Sharp

-0.63

PORT

-0.59

bart

-0.59

ANN

-0.58

."

-0.57

Quantity

-0.55

 Sapphire

-0.55

ani

-0.54

POSITIVE LOGITS

 spearheaded

0.78

 accompanies

0.78

 originally

0.73

 owns

0.71

 ordinarily

0.69

idth

0.69

 oversees

0.68

 resided

0.68

 comprises

0.68

 normally

0.68

Activations Density 0.155%

proper nouns or names of specific entities

the phrase "which" followed by various forms of information or descriptions

No Comments

No Known Activations