INDEX

Explanations

structures or components related to technical specifications or data tables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Oye

-0.70

 Mishra

-0.68

 Bobby

-0.67

 Johan

-0.66

 Gandhi

-0.66

Johan

-0.65

 XXVI

-0.63

 Sanchez

-0.62

POSITIVE LOGITS

 Levine

0.74

 Schmitz

0.72

بوابة

0.72

⎩

0.71

 Whitley

0.71

 Finley

0.67

 Sheppard

0.66

 Kina

0.66

 Jacobson

0.65

 Morley

0.65

Activations Density 1.869%

structures or components related to technical specifications or data tables

No Comments

No Known Activations