INDEX

Explanations

comparisons or quantities using the word "than"

oai_token-act-pair · gpt-3.5-turbo

comparisons or quantifications of amounts or numbers

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

EMENT

-0.80

Interstitial

-0.77

ç·

-0.76

ALSE

-0.71

ALE

-0.70

ilic

-0.69

DH

-0.68

ãĤ¼ãĤ¦ãĤ¹

-0.67

ä½¿

-0.67

microsoft

-0.67

POSITIVE LOGITS

whelming

0.81

 doubling

0.67

0.65

0.63

etheless

0.62

race

0.62

0.61

Activations Density 0.042%

comparisons or quantities using the word "than"

comparisons or quantifications of amounts or numbers

No Comments

No Known Activations