INDEX

Explanations

instances of the word "did" in different 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>

-2.66

Autoritní

-0.74

AsUp

-0.71

Geplaatst

-0.69

ftagPool

-0.64

 betweenstory

-0.64

 autorytatywna

-0.64

Jeografia

-0.64

addCriterion

-0.64

PageRoute

-0.63

POSITIVE LOGITS

 disagre

2.08

 maneu

2.02

 reluct

2.00

 unspeak

1.97

 impra

1.92

 affor

1.91

 apprehen

1.89

 shenan

1.83

 unwarran

1.81

 indescri

1.80

Activations Density 0.119%

instances of the word "did" in different contexts

No Comments

No Known Activations