INDEX

Explanations

numerical values or quantities

oai_token-act-pair · gpt-3.5-turbo

occurrences of the number "2" in various contexts

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

rolet

-0.77

£ı

-0.64

 Lauder

-0.63

 swearing

-0.62

actionDate

-0.61

Ĥİ

-0.60

Fas

-0.58

 sacked

-0.57

woo

-0.57

 Maced

-0.56

POSITIVE LOGITS

Â½

1.05

nd

0.96

0.93

WD

0.92

0.91

ND

0.90

rd

0.89

DS

0.88

DO

0.86

ÃĹ

0.85

Activations Density 0.176%

numerical values or quantities

occurrences of the number "2" in various contexts

No Comments

No Known Activations