INDEX

Explanations

measurements of length

oai_token-act-pair · gpt-3.5-turbo

references to measurements of length

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

eers

-1.00

eer

-0.89

eering

-0.75

eor

-0.72

oras

-0.72

tical

-0.70

ILLE

-0.69

BA

-0.68

dinand

-0.68

unin

-0.67

POSITIVE LOGITS

shed

1.02

 length

0.98

 lengths

0.94

iest

0.81

length

0.79

wise

0.77

 ILCS

0.76

Length

0.76

staking

0.75

 circumference

0.74

Activations Density 0.018%

measurements of length

references to measurements of length

No Comments

No Known Activations