INDEX

Explanations

comparisons indicating that something is not as bad as perceived

oai_token-act-pair · gpt-3.5-turbo

comparative phrases indicating relative conditions or qualities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

rev

-0.69

uld

-0.67

ainer

-0.67

antage

-0.65

acent

-0.64

iverse

-0.64

itory

-0.63

REE

-0.62

heast

-0.62

reated

-0.62

POSITIVE LOGITS

lihood

0.85

©¶æ

0.83

pects

0.79

 opposed

0.77

 evidenced

0.76

bestos

0.74

 possible

0.73

ĳå£«

0.71

 usual

0.68

criptions

0.68

Activations Density 0.088%

comparisons indicating that something is not as bad as perceived

comparative phrases indicating relative conditions or qualities

No Comments

No Known Activations