INDEX

Explanations

phrases indicating support or favor in legal or political contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 Ibis

-0.59

 zasi

-0.57

ClientSize

-0.53

nhi

-0.52

required

-0.52

 ibis

-0.52

URA

-0.51

ваш

-0.51

"]);

-0.50

 Bourgoin

-0.50

POSITIVE LOGITS

RunWith

0.69

 supports

0.69

 favoring

0.68

 respald

0.68

 backing

0.67

 apoyar

0.67

InitStruct

0.65

 Supports

0.64

supports

0.62

ItemBackground

0.62

Activations Density 0.413%

phrases indicating support or favor in legal or political contexts

No Comments

No Known Activations