INDEX

Explanations

phrases related to beliefs or assumptions

oai_token-act-pair · gpt-3.5-turbo

phrases indicating beliefs or assumptions about individuals or situations

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

Interstitial

-0.82

enegger

-0.70

cloth

-0.68

 Jackets

-0.65

Cola

-0.65

learn

-0.62

ventory

-0.61

backer

-0.61

 Mountains

-0.61

unciation

-0.59

POSITIVE LOGITS

ril

0.69

 Beir

0.64

atis

0.62

MpServer

0.61

inery

0.61

 errone

0.59

 quart

0.58

 probable

0.58

 incorrectly

0.58

istani

0.58

Activations Density 0.061%

phrases related to beliefs or assumptions

phrases indicating beliefs or assumptions about individuals or situations

No Comments

No Known Activations