INDEX

Explanations

various roles and positions in professional contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ChildScrollView

-0.88

ContentAlignment

-0.84

AndEndTag

-0.84

__":

-0.83

__':

-0.82

 oprot

-0.81

 crdi

-0.78

migrationBuilder

-0.77

ReusableCell

-0.77

 esternos

-0.77

POSITIVE LOGITS

0.57

0.53

0.52

0.49

0.45

CEO

0.43

0.42

Re

0.42

The

0.42

Activations Density 0.003%

various roles and positions in professional contexts

No Comments

No Known Activations