INDEX

Explanations

specific geographical locations and institutional affiliations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 GenerationType

-0.71

 snippetHide

-0.68

مصادر

-0.60

 AssemblyCulture

-0.56

__((

-0.56

談社

-0.56

NameInMap

-0.55

saraba

-0.55

Enllaços

-0.55

NameValuePair

-0.55

POSITIVE LOGITS

CA

0.77

MN

0.68

GA

0.67

BA

0.67

MI

0.66

CT

0.66

MA

0.66

LA

0.65

DE

0.63

BC

0.61

Activations Density 0.344%

specific geographical locations and institutional affiliations

No Comments

No Known Activations