INDEX

Explanations

references to the word "Hop"

oai_token-act-pair · gpt-3.5-turbo

references to hops in the context of brewing or beer

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Downloadha

-0.76

ateral

-0.76

 payable

-0.72

etheless

-0.68

 withd

-0.66

 conclud

-0.65

 confir

-0.65

ude

-0.65

 behold

-0.62

UCT

-0.62

POSITIVE LOGITS

eful

1.40

efully

1.27

Hop

1.22

eless

1.04

hop

1.03

retty

0.93

Hop

0.92

emaker

0.86

shots

0.85

lite

0.84

Activations Density 0.024%

references to the word "Hop"

references to hops in the context of brewing or beer

No Comments

No Known Activations