INDEX

Explanations

word parts or a specific pattern that appear repeatedly but do not form coherent text

oai_token-act-pair · gpt-3.5-turbo

words related to specific actions or activities

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

Negative Logits

 suspic

-0.69

 reluct

-0.67

PDATE

-0.64

 VIDE

-0.63

 cumbers

-0.63

ModLoader

-0.62

ÙĴ

-0.62

 convol

-0.62

WARN

-0.61

DERR

-0.61

POSITIVE LOGITS

ensis

1.18

aii

0.84

gmail

0.84

ocious

0.82

yahoo

0.79

[_

0.77

iii

0.74

pai

0.73

ii

0.73

yan

0.73

Activations Density 0.364%

word parts or a specific pattern that appear repeatedly but do not form coherent text

words related to specific actions or activities

No Known Activations