INDEX

Explanations

instances where someone or something is being considered or evaluated as a potential choice or selection

oai_token-act-pair · gpt-3.5-turbo

terms related to potential candidates or selections 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

©¶æ

-0.82

ipl

-0.78

imb

-0.65

mt

-0.65

arus

-0.65

isson

-0.64

ided

-0.64

VERTIS

-0.63

iries

-0.62

raining

-0.62

POSITIVE LOGITS

 contender

1.06

 contenders

0.89

 bidder

0.85

 candidate

0.73

 frontrunner

0.73

 blocker

0.70

ä½¿

0.70

ä»£

0.69

 among

0.69

 buyer

0.69

Activations Density 0.114%

instances where someone or something is being considered or evaluated as a potential choice or selection

terms related to potential candidates or selections in various contexts

No Comments

No Known Activations