INDEX

Explanations

words related to expressing suspicion or uncertainty

oai_token-act-pair · gpt-3.5-turbo

phrases that indicate speculation or questioning

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

olves

-0.70

ords

-0.69

rawdownloadcloneembedreportprint

-0.63

hed

-0.61

 REPL

-0.60

ufact

-0.60

BuyableInstoreAndOnline

-0.60

ighed

-0.58

interstitial

-0.58

 dynam

-0.56

POSITIVE LOGITS

 albeit

0.91

 alas

0.89

 however

0.81

 somew

0.80

 although

0.76

 anecd

0.72

 lest

0.72

 though

0.71

Dri

0.70

perhaps

0.70

Activations Density 0.183%

words related to expressing suspicion or uncertainty

phrases that indicate speculation or questioning

No Comments

No Known Activations