INDEX

Explanations

words related to legislation and legal actions

oai_token-act-pair · gpt-3.5-turbo

symbols or unique characters related to significant entities or concepts

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

 redes

-0.65

course

-0.64

 assum

-0.64

 appro

-0.64

esta

-0.63

 asses

-0.62

mine

-0.60

 entail

-0.59

orr

-0.59

 rele

-0.58

POSITIVE LOGITS

 VIDE

0.85

 Thousands

0.82

ĸļ

0.79

*/(

0.79

 Latest

0.79

 Tonight

0.76

POL

0.75

 Yesterday

0.75

SHARE

0.71

 Protesters

0.70

Activations Density 0.045%

words related to legislation and legal actions

symbols or unique characters related to significant entities or concepts

No Comments

No Known Activations