INDEX

Explanations

expressions related to completing tasks or satisfying requirements

oai_token-act-pair · gpt-3.5-turbo

instances of the word "tick" and its variations

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

¬¼

-0.68

cov

-0.68

IZE

-0.66

 Dakota

-0.66

ocal

-0.63

ocally

-0.63

equality

-0.62

 ILCS

-0.61

icably

-0.60

ufact

-0.60

POSITIVE LOGITS

lish

1.22

ety

1.10

lers

1.06

led

1.05

ling

1.01

les

1.01

ched

0.94

leness

0.91

stone

0.89

eworthy

0.87

Activations Density 0.058%

expressions related to completing tasks or satisfying requirements

instances of the word "tick" and its variations

No Comments

No Known Activations