INDEX

Explanations

phrases indicating location or setting

oai_token-act-pair · gpt-3.5-turbo

locations or conditions expressed by the word "where."

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

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

apult

-0.79

rolet

-0.77

aiden

-0.72

ME

-0.65

Pwr

-0.65

redit

-0.64

termin

-0.64

undo

-0.64

nesday

-0.63

 Quarterly

-0.63

POSITIVE LOGITS

upon

1.36

soever

0.92

 there

0.92

 nobody

0.86

we

0.85

 they

0.85

 everyone

0.84

 neither

0.80

you

0.80

abouts

0.80

Activations Density 0.091%

phrases indicating location or setting

locations or conditions expressed by the word "where."

No Comments

No Known Activations