INDEX

Explanations

phrases describing physical actions involving hands and arms

oai_token-act-pair · gpt-3.5-turbo

the word "as" used in various contexts to create comparisons or describe actions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

iosyncr

-0.76

Planet

-0.66

è£ħ

-0.64

Manufact

-0.63

quist

-0.63

Gender

-0.62

tty

-0.59

ãĤ¼

-0.59

Ess

-0.58

Intern

-0.58

POSITIVE LOGITS

phy

0.91

 they

0.88

 dusk

0.85

piring

0.84

bestos

0.81

 soon

0.81

 follows

0.80

 well

0.80

he

0.80

pired

0.78

Activations Density 0.122%

phrases describing physical actions involving hands and arms

the word "as" used in various contexts to create comparisons or describe actions

No Comments

No Known Activations