INDEX

Explanations

words starting with 'wh'

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "wh."

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

Not in Any Lists

No Comments

Negative Logits

rella

-0.75

 Rein

-0.73

alia

-0.71

 Desert

-0.66

tera

-0.65

 Celeb

-0.65

rez

-0.65

ovic

-0.64

 Variant

-0.64

 Romania

-0.64

POSITIVE LOGITS

wh

3.50

Wh

1.86

wh

1.85

Wh

1.62

WH

1.39

thw

1.35

 whipping

1.16

whe

1.10

th

1.09

 whale

1.07

Activations Density 0.008%

words starting with 'wh'

occurrences of the word "wh."

No Comments

No Known Activations