INDEX

Explanations

phrases related to division or categorization

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate division or categorization

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

tor

-0.70

zai

-0.69

tun

-0.66

JM

-0.64

 insulted

-0.64

entimes

-0.64

die

-0.63

 onwards

-0.63

heit

-0.61

 challeng

-0.59

POSITIVE LOGITS

 thirds

0.87

qqa

0.77

ãĤ©

0.76

 categories

0.74

 submission

0.73

clusions

0.73

perse

0.71

itialized

0.69

Sequ

0.69

İĭ

0.68

Activations Density 0.044%

phrases related to division or categorization

phrases that indicate division or categorization

No Comments

No Known Activations