INDEX

Explanations

instances related to the initial phase or starting point of something

oai_token-act-pair · gpt-3.5-turbo

terms related to introductory or preliminary stages

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

 Dame

-0.73

 ..."

-0.69

greg

-0.65

scribe

-0.64

 haun

-0.64

 SPORTS

-0.63

stained

-0.63

 Journalists

-0.63

well

-0.63

steen

-0.63

POSITIVE LOGITS

 initial

3.40

initial

2.43

Initial

2.28

 Initial

2.18

 initially

1.84

 preliminary

1.64

 initialization

1.49

 original

1.48

 immediate

1.36

 initialize

1.33

Activations Density 0.012%

instances related to the initial phase or starting point of something

terms related to introductory or preliminary stages

No Known Activations