INDEX

Explanations

references to specific authors or studies in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 ModelExpression

-0.90

</tfoot>

-0.87

NUMX

-0.84

AntiForgeryToken

-0.80

SBATCH

-0.80

]='\

-0.79

EDEFAULT

-0.77

 snippetHide

-0.77

$)$

-0.75

 للمعارف

-0.75

POSITIVE LOGITS

0.57

0.55

et

0.54

0.47

<u>

0.45

ut

0.45

int

0.44

py

0.43

se

0.42

Activations Density 0.224%

references to specific authors or studies in scientific contexts

No Comments

No Known Activations