INDEX

Explanations

questions starting with the word "How"

oai_token-act-pair · gpt-3.5-turbo

questions formatted with "How" or "What"

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

 fide

-0.63

 grounds

-0.61

ptions

-0.59

IENT

-0.59

goers

-0.58

 Feld

-0.58

agonists

-0.57

 Walton

-0.57

Args

-0.56

 Skydragon

-0.55

POSITIVE LOGITS

soever

1.07

ever

1.02

beit

0.98

ells

0.87

ling

0.86

itzer

0.78

leep

0.75

bill

0.75

ls

0.73

dy

0.72

Activations Density 0.060%

questions starting with the word "How"

questions formatted with "How" or "What"

No Comments

No Known Activations