INDEX

Explanations

the word "be" in various contexts

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

New Auto-Interp

Configuration

jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.10.hook_resid_post_16384

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

chanind/openwebtext-gemma

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

standard

Context Size

1,024

Dataset

ctigges/openwebtext-gemma-1024-cl

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

<bos>

-2.68

 which

-0.65

-0.63

and

-0.62

-0.59

lang

-0.59

//

-0.59

 didn

-0.59

namespace

-0.59

Referències

-0.59

POSITIVE LOGITS

 accla

1.70

 practition

1.59

 stockholm

1.57

ftu

1.56

 lidl

1.56

 milf

1.56

 volunte

1.55

 fatis

1.52

 maneu

1.50

 suspic

1.50

Activations Density 0.111%

the word "be" in various contexts

No Comments

No Known Activations