INDEX

Explanations

text related to authorization or permission

oai_token-act-pair · gpt-3.5-turbo

specific characters or symbols that are repeated throughout 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

 puff

-0.71

 snail

-0.67

è¦ļéĨĴ

-0.67

 orgasm

-0.66

 stump

-0.66

 contrace

-0.65

 ende

-0.65

 endings

-0.64

 idea

-0.64

 mushroom

-0.63

POSITIVE LOGITS

said

1.03

ï¸ı

0.96

tra

0.86

ttp

0.85

Â¯

0.83

east

0.81

cause

0.81

mr

0.80

then

0.80

sn

0.80

Activations Density 0.189%

text related to authorization or permission

specific characters or symbols that are repeated throughout the text

No Comments

No Known Activations