INDEX

Explanations

technical and scientific terms related to physics and research

oai_token-act-pair · gpt-3.5-turbo

keywords related to scientific and institutional frameworks

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

Cola

-0.60

elsen

-0.60

owe

-0.57

lehem

-0.55

NAS

-0.52

CHR

-0.52

oshenko

-0.52

bilt

-0.52

cale

-0.51

ãĥ´

-0.50

POSITIVE LOGITS

apters

0.66

origin

0.64

gradient

0.59

anship

0.59

reements

0.59

 Dialogue

0.56

enegger

0.55

ourses

0.54

arsity

0.54

agonists

0.52

Activations Density 1.220%

technical and scientific terms related to physics and research

keywords related to scientific and institutional frameworks

No Comments

No Known Activations