INDEX

Explanations

numeric figures related to quantities or measurements

oai_token-act-pair · gpt-3.5-turbo

quantifiable measurements or counts related to various topics

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

rum

-0.76

olic

-0.56

GI

-0.56

gee

-0.55

ellar

-0.55

rology

-0.54

 literature

-0.53

activ

-0.53

 Phys

-0.53

 Canary

-0.52

POSITIVE LOGITS

 apiece

1.68

poons

1.14

per

0.95

paces

0.91

omething

0.87

 consecut

0.85

 total

0.79

awatts

0.79

renheit

0.76

 respectively

0.75

Activations Density 0.249%

numeric figures related to quantities or measurements

quantifiable measurements or counts related to various topics

No Comments

No Known Activations