INDEX

Explanations

occurrences of the word "in"

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>

-3.18

ⓧ

-0.87

/**

-0.67

vece

-0.63

<?

-0.61

protoc

-0.60

 springfox

-0.59

mergeFrom

-0.58

-0.56

Geplaatst

-0.56

POSITIVE LOGITS

 lele

1.16

 lamborghini

1.10

 maneu

1.10

 accla

1.09

 affor

1.07

 michelin

1.07

 vété

1.07

 malheure

1.06

 corsair

1.06

 déchir

1.06

Activations Density 0.562%

occurrences of the word "in"

No Comments

No Known Activations