INDEX

Explanations

phrases indicating agreement or disagreement with a particular plan or idea

oai_token-act-pair · gpt-3.5-turbo

expressions of agreement or disagreement with plans or opinions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

ëĭ

-0.68

 lookup

-0.62

 datas

-0.61

egu

-0.59

 Fortune

-0.59

Ops

-0.58

 Blizz

-0.58

Moz

-0.58

 Lever

-0.57

 Worlds

-0.57

POSITIVE LOGITS

galitarian

0.88

0.87

 disagrees

0.82

 endorse

0.82

 endorsing

0.78

 dismissing

0.77

 recommending

0.75

 disagree

0.74

 vehemently

0.74

Rate

0.74

Activations Density 0.289%

phrases indicating agreement or disagreement with a particular plan or idea

expressions of agreement or disagreement with plans or opinions

No Comments

No Known Activations