INDEX

Explanations

details related to specific events taking place over a period of time

oai_token-act-pair · gpt-3.5-turbo

instances of the word "while"

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

aer

-0.84

atter

-0.81

iotic

-0.76

ologically

-0.76

ettle

-0.74

hack

-0.73

elled

-0.72

omer

-0.72

arse

-0.69

iosyncr

-0.69

POSITIVE LOGITS

 researching

0.91

 browsing

0.91

 touring

0.86

 attending

0.84

 visiting

0.81

 compiling

0.80

 commuting

0.80

 maintaining

0.79

 typing

0.78

 airing

0.77

Activations Density 0.047%

details related to specific events taking place over a period of time

instances of the word "while"

No Comments

No Known Activations