INDEX

Explanations

phrases indicating reasons or explanations

oai_token-act-pair · gpt-3.5-turbo

the word "why" used in various contexts throughout the text

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

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

ãĥ¼ãĤ¯

-0.78

ty

-0.67

rop

-0.67

aith

-0.67

ãĥĥãĥĪ

-0.63

bow

-0.63

bor

-0.62

zman

-0.60

result

-0.57

iox

-0.57

POSITIVE LOGITS

why

0.91

we

0.89

 they

0.81

soever

0.76

 many

0.73

it

0.72

 Canaver

0.72

terday

0.66

ratulations

0.66

 there

0.66

Activations Density 0.048%

phrases indicating reasons or explanations

the word "why" used in various contexts throughout the text

No Comments

No Known Activations