INDEX

Explanations

words related to legal and political contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of a specific character

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

 Glacier

-0.69

 FANT

-0.66

pid

-0.65

iage

-0.61

 Leopard

-0.60

assian

-0.60

 Piece

-0.59

romeda

-0.59

CoC

-0.58

 Jinn

-0.58

POSITIVE LOGITS

ï¸ı

0.98

_>

0.89

then

0.80

whe

0.78

âĵĺ

0.77

cause

0.74

added

0.73

 alas

0.72

Tx

0.71

sure

0.71

Activations Density 0.199%

words related to legal and political contexts

occurrences of a specific character

No Comments

No Known Activations