INDEX

Explanations

texts related to updates, releases, and changes

oai_token-act-pair · gpt-3.5-turbo

instances of a specific symbol or 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

fed

-0.74

 shack

-0.65

 confused

-0.64

 scatter

-0.64

 decomp

-0.63

 dangling

-0.63

 cyan

-0.63

 lying

-0.61

 dwelling

-0.61

 habit

-0.60

POSITIVE LOGITS

į

0.93

ı

0.86

º

0.86

§

0.83

¹

0.80

Ī

0.80

imester

0.78

â

0.78

âĢķ

0.77

soType

0.77

Activations Density 0.304%

texts related to updates, releases, and changes

instances of a specific symbol or character

No Comments

No Known Activations