INDEX

Explanations

words related to physical activities or tasks

oai_token-act-pair · gpt-3.5-turbo

terms related to choreography and dance

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

 plur

-0.72

yip

-0.71

blank

-0.66

berman

-0.65

 Reloaded

-0.65

 Civic

-0.64

 Sherman

-0.64

uyomi

-0.63

 Pathfinder

-0.60

 Elliot

-0.59

POSITIVE LOGITS

ographed

1.66

ograph

1.24

ograp

1.23

 chore

1.17

ographs

1.13

ography

1.13

ographer

1.09

ographers

1.00

ographic

0.91

strip

0.91

Activations Density 0.011%

words related to physical activities or tasks

terms related to choreography and dance

No Comments

No Known Activations