INDEX

Explanations

phrases related to legal terms or people's names starting with "Str"

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SHIP

-0.69

 secrecy

-0.63

 pleas

-0.61

eers

-0.61

 Reeves

-0.59

 hypers

-0.58

 Garland

-0.57

 Derby

-0.57

eer

-0.57

 courts

-0.57

POSITIVE LOGITS

ategy

1.59

ategic

1.51

ateg

1.44

anded

1.39

angers

1.34

atton

1.33

icken

1.30

ife

1.25

aditional

1.23

ained

1.21

Activations Density 0.022%

phrases related to legal terms or people's names starting with "Str"

No Comments

No Known Activations