INDEX

Explanations

references to "features" in various 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-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

PVA

-0.99

Alp

-0.92

ALP

-0.91

ILON

-0.89

 BorderRadius

-0.89

thschild

-0.87

LDA

-0.87

 pessoais

-0.87

 clearColor

-0.87

 scorso

-0.87

POSITIVE LOGITS

 features

1.89

 feature

1.69

 Features

1.62

Features

1.57

features

1.54

 FEATURE

1.50

 Feature

1.45

 FEATURES

1.41

Feature

1.39

FEATURE

1.34

Activations Density 0.042%

references to "features" in various contexts

No Comments

No Known Activations