INDEX

Explanations

JSON or programming-related text patterns

oai_token-act-pair · gpt-3.5-turbo

punctuation and formatting elements 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

lik

-0.71

 sugg

-0.65

romeda

-0.64

 newsp

-0.63

 certific

-0.62

 surv

-0.62

 charm

-0.61

 pens

-0.61

 confir

-0.61

 challeng

-0.61

POSITIVE LOGITS

tesy

0.89

english

0.78

soType

0.77

BuyableInstoreAndOnline

0.77

std

0.77

acity

0.74

 "$:/

0.71

taboola

0.71

arte

0.70

["

0.69

Activations Density 0.042%

JSON or programming-related text patterns

punctuation and formatting elements in the text

No Comments

No Known Activations