INDEX

Explanations

words related to laws or regulations

oai_token-act-pair · gpt-3.5-turbo

instances of specific letters or characters in the text

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

 Watkins

-0.72

KP

-0.70

Ĥİ

-0.69

Kau

-0.67

KS

-0.66

 Kern

-0.66

ASA

-0.65

 Leilan

-0.65

 Leopard

-0.64

 Tactics

-0.64

POSITIVE LOGITS

vernment

1.02

ancial

0.89

Ì¶

0.85

undred

0.84

É

0.83

roc

0.80

actly

0.80

oyal

0.80

ploy

0.80

iable

0.79

Activations Density 0.172%

words related to laws or regulations

instances of specific letters or characters in the text

No Comments

No Known Activations