INDEX

Explanations

positive evaluations or approvals in sentences

oai_token-act-pair · gpt-3.5-turbo

phrases that express approval or positivity about various topics

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

hod

-0.72

 largeDownload

-0.71

yrinth

-0.68

cled

-0.66

cul

-0.66

geon

-0.65

ao

-0.64

è»

-0.64

chan

-0.63

geons

-0.63

POSITIVE LOGITS

 happened

0.85

 happening

0.84

 happen

0.80

 outwe

0.78

 happens

0.75

iverse

0.74

ifier

0.73

 occurring

0.72

 Happ

0.69

 outweigh

0.69

Activations Density 0.033%

positive evaluations or approvals in sentences

phrases that express approval or positivity about various topics

No Comments

No Known Activations