INDEX

Explanations

legal or regulatory terms

oai_token-act-pair · gpt-3.5-turbo

instances of the word "Under" followed by numerical values

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aukee

-0.75

bernatorial

-0.63

mov

-0.61

-0.60

 Scand

-0.57

 rubbish

-0.56

 scratch

-0.56

 distur

-0.56

assic

-0.56

 offensively

-0.55

POSITIVE LOGITS

neath

1.34

lying

1.17

graduate

1.06

Ļ½

0.97

lining

0.96

stant

0.96

mining

0.95

cover

0.95

stood

0.92

flows

0.91

Activations Density 0.024%

legal or regulatory terms

instances of the word "Under" followed by numerical values

No Comments

No Known Activations