INDEX

Explanations

phrases related to human faces

oai_token-act-pair · gpt-3.5-turbo

references to faces or the concept of a "face" in various contexts

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

æ©Ł

-0.88

icult

-0.77

icultural

-0.72

RY

-0.66

>>\

-0.65

ighting

-0.65

iculture

-0.64

ary

-0.63

CAST

-0.63

reat

-0.62

POSITIVE LOGITS

plate

0.96

 faces

0.94

plant

0.93

 face

0.93

face

0.86

BOOK

0.86

offs

0.83

faces

0.82

hog

0.81

beard

0.80

Activations Density 0.031%

phrases related to human faces

references to faces or the concept of a "face" in various contexts

No Comments

No Known Activations