INDEX

Explanations

words related to belief, doubt, and support

oai_token-act-pair · gpt-3.5-turbo

concepts of credibility and doubt in assertions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Ascension

-0.60

 commute

-0.55

 downtime

-0.50

imar

-0.50

 journeys

-0.49

Ath

-0.49

 itiner

-0.49

 Parkinson

-0.48

Submit

-0.48

Fre

-0.48

POSITIVE LOGITS

 onto

0.89

PsyNetMessage

0.86

gradient

0.81

enance

0.77

 unto

0.74

papers

0.74

vim

0.72

 into

0.68

@#

0.67

steam

0.67

Activations Density 0.396%

words related to belief, doubt, and support

concepts of credibility and doubt in assertions

No Comments

No Known Activations