INDEX

Explanations

the word "Analyze" or similar variations

oai_token-act-pair · gpt-3.5-turbo

terms related to analysis and analytical processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Leilan

-0.73

 Hale

-0.66

 guiActiveUnfocused

-0.66

 Panic

-0.63

 Worlds

-0.63

 Redemption

-0.62

 Origin

-0.62

 Sandwich

-0.60

 Kelvin

-0.60

 Doctrine

-0.60

POSITIVE LOGITS

tical

1.38

sts

1.37

zed

1.29

zing

1.28

zer

1.25

tic

1.22

ctions

1.22

zes

1.18

zers

1.17

ze

1.13

Activations Density 0.053%

the word "Analyze" or similar variations

terms related to analysis and analytical processes

No Comments

No Known Activations