INDEX

Explanations

phrases or words related to categorization or classification

oai_token-act-pair · gpt-3.5-turbo

phrases indicating categorization or classification

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ãĤ¦ãĤ¹

-0.69

 overcame

-0.68

 sacrific

-0.59

reetings

-0.59

HAM

-0.58

NECT

-0.57

ankind

-0.56

imentary

-0.55

nz

-0.55

Score

-0.55

POSITIVE LOGITS

 category

0.92

 obscurity

0.90

BuyableInstoreAndOnline

0.78

 categories

0.78

 trap

0.77

 pitfalls

0.75

pmwiki

0.73

 realms

0.72

emort

0.71

 fallacy

0.70

Activations Density 0.088%

phrases or words related to categorization or classification

phrases indicating categorization or classification

No Comments

No Known Activations