INDEX

Explanations

terms related to making a strong effort or exerting pressure

oai_token-act-pair · gpt-3.5-turbo

instances of the word "push" indicating an attempt to influence or promote action

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

abol

-0.78

redited

-0.71

omial

-0.67

BuyableInstoreAndOnline

-0.66

 poss

-0.66

 Chaff

-0.65

 Recogn

-0.64

 Surviv

-0.64

odied

-0.61

 Dealer

-0.61

POSITIVE LOGITS

 push

0.90

push

0.88

back

0.87

 pushing

0.83

chairs

0.81

overs

0.81

 pushes

0.80

boxes

0.78

Push

0.76

arte

0.76

Activations Density 0.017%

terms related to making a strong effort or exerting pressure

instances of the word "push" indicating an attempt to influence or promote action

No Comments

No Known Activations