INDEX

Explanations

words related to credibility or authenticity

oai_token-act-pair · gpt-3.5-turbo

terms related to belief or credibility

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

Ò

-0.80

hap

-0.73

meal

-0.70

 combatants

-0.64

 Feature

-0.63

 Pastebin

-0.60

Elm

-0.60

Í

-0.59

ĵĺ

-0.59

Ô

-0.58

POSITIVE LOGITS

enza

1.30

ulously

1.23

ulous

1.10

ulent

1.04

encing

1.02

entials

1.00

itous

0.97

iting

0.96

itious

0.95

ences

0.94

Activations Density 0.040%

words related to credibility or authenticity

terms related to belief or credibility

No Comments

No Known Activations