INDEX

Explanations

expressions referring to quantity or degree

oai_token-act-pair · gpt-3.5-turbo

instances of the phrase "how much."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

İĭ

-0.86

swick

-0.73

idon

-0.72

fman

-0.71

yg

-0.71

utton

-0.71

oresc

-0.69

agate

-0.68

atures

-0.68

ATURES

-0.68

POSITIVE LOGITS

 appreciated

0.79

ado

0.79

 esteemed

0.72

 MUCH

0.71

 else

0.70

 effort

0.65

 emphasis

0.65

 simpler

0.63

fun

0.63

NESS

0.62

Activations Density 0.057%

expressions referring to quantity or degree

instances of the phrase "how much."

No Comments

No Known Activations