INDEX

Explanations

words containing the prefix "up"

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

 mileage

-0.65

ãĥł

-0.63

 Caldwell

-0.61

 Rosenthal

-0.59

Abs

-0.58

 corrid

-0.58

Â¯Â¯Â¯Â¯

-0.57

 Curiosity

-0.57

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.57

OB

-0.56

POSITIVE LOGITS

dates

1.53

olicy

1.24

dating

1.09

edia

1.07

stairs

1.07

olitan

1.07

odcast

1.07

rint

1.06

reme

1.06

resents

1.05

Activations Density 0.060%

words containing the prefix "up"

No Comments

No Known Activations