INDEX

Explanations

words related to negative appearance or attributes

oai_token-act-pair · gpt-3.5-turbo

references to the concept of "ugliness."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ership

-0.97

ingham

-0.95

aver

-0.89

agall

-0.86

owder

-0.86

akings

-0.86

iasm

-0.85

erve

-0.84

ittee

-0.80

unes

-0.79

POSITIVE LOGITS

 ugly

1.10

 adolesc

0.89

 beasts

0.79

 elephant

0.75

 scar

0.74

 crap

0.73

 mole

0.72

 nasty

0.72

 spectacle

0.70

 scars

0.70

Activations Density 0.019%

words related to negative appearance or attributes

references to the concept of "ugliness."

No Comments

No Known Activations