INDEX

Explanations

numeric or symbolic characters that appear at the end of words

oai_token-act-pair · gpt-3.5-turbo

sequences or symbols that signify a particular emphasis or pattern, likely related to coded or specialized language

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

Mub

-0.74

bda

-0.72

 rake

-0.71

Downloadha

-0.68

 disenfranch

-0.65

ukong

-0.63

bucks

-0.62

 Peel

-0.61

 warr

-0.60

 levers

-0.60

POSITIVE LOGITS

ħ

1.11

Ĭ

0.99

¡

0.99

Į

0.98

İ

0.96

Û

0.92

ŀ

0.88

Ĩ

0.87

Ĥª

0.85

¾

0.85

Activations Density 0.020%

numeric or symbolic characters that appear at the end of words

sequences or symbols that signify a particular emphasis or pattern, likely related to coded or specialized language

No Comments

No Known Activations