INDEX

Explanations

references to news programming and television stations

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

makeConstraints

-0.90

 ModelExpression

-0.88

uxxxx

-0.86

IntoConstraints

-0.85

 AssemblyCulture

-0.83

ftagPool

-0.81

UnusedPrivate

-0.81

ImageContext

-0.78

DockStyle

-0.78

 مشين

-0.76

POSITIVE LOGITS

 lẫn

0.52

何故

0.50

press

0.46

Press

0.46

 rivals

0.46

 Press

0.45

0.44

irei

0.44

 press

0.44

 avenir

0.44

Activations Density 0.822%

references to news programming and television stations

No Comments

No Known Activations