INDEX

Explanations

phrases related to various actions or states of having

oai_token-act-pair · gpt-3.5-turbo

instances of the word "having."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ocol

-0.78

etter

-0.63

 ........

-0.63

 Dispatch

-0.62

tel

-0.59

 hostage

-0.58

hooting

-0.58

 Echo

-0.57

etting

-0.57

osa

-0.56

POSITIVE LOGITS

 undergone

0.90

 been

0.84

drawn

0.82

erers

0.81

 eaten

0.79

AMI

0.79

 listened

0.74

stood

0.73

 done

0.70

gotten

0.69

Activations Density 0.033%

phrases related to various actions or states of having

instances of the word "having."

No Comments

No Known Activations