INDEX

Explanations

negative statements or uncertainties

oai_token-act-pair · gpt-3.5-turbo

negative contractions and phrases suggesting a lack of success or fulfillment

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

kamp

-0.68

ãģ®ç

-0.65

 arsen

-0.62

ologically

-0.58

Reviewer

-0.57

 appropri

-0.57

udic

-0.56

itech

-0.55

agate

-0.55

 administr

-0.54

POSITIVE LOGITS

 relent

0.79

 dissu

0.77

stop

0.73

 dull

0.70

 appe

0.68

 smoothly

0.66

 deter

0.66

 smooth

0.65

 quiet

0.65

aired

0.65

Activations Density 0.216%

negative statements or uncertainties

negative contractions and phrases suggesting a lack of success or fulfillment

No Comments

No Known Activations