INDEX

Explanations

mentions of skepticism or doubtful attitudes

oai_token-act-pair · gpt-3.5-turbo

instances of skepticism towards various subjects or claims

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

apeake

-0.73

shows

-0.72

erry

-0.70

Lay

-0.68

updated

-0.68

amaz

-0.68

Interstitial

-0.65

nice

-0.65

united

-0.64

usable

-0.64

POSITIVE LOGITS

 skepticism

0.94

 skept

0.90

 skeptics

0.90

icism

0.86

 skeptical

0.81

chell

0.79

cius

0.78

 disbel

0.76

 disbelief

0.75

 scept

0.74

Activations Density 0.026%

mentions of skepticism or doubtful attitudes

instances of skepticism towards various subjects or claims

No Comments

No Known Activations