INDEX

Explanations

words related to disproving or debunking information or theories

oai_token-act-pair · gpt-3.5-turbo

terms related to debunking or disproving claims and myths

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

ebus

-0.73

emetery

-0.72

arta

-0.72

estial

-0.67

engeance

-0.66

estate

-0.66

orneys

-0.65

Eye

-0.64

aned

-0.64

itizens

-0.63

POSITIVE LOGITS

 debunked

1.02

 debunk

1.00

 unfounded

0.93

 dispro

0.87

 baseless

0.86

 assertions

0.85

 falsehood

0.83

 misconceptions

0.82

 hypotheses

0.79

 corrobor

0.78

Activations Density 0.096%

words related to disproving or debunking information or theories

terms related to debunking or disproving claims and myths

No Comments

No Known Activations