INDEX

Explanations

references to specific events or details related to time and recognition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 annan

-0.65

 chaves

-0.56

 defaultstate

-0.55

 annen

-0.51

Rè

-0.50

 décé

-0.48

keyCode

-0.48

 antigas

-0.48

 sécher

-0.47

InstrumentedTest

-0.47

POSITIVE LOGITS

RenderAtEndOf

0.83

 ever

0.81

 first

0.74

 tiên

0.73

TagMode

0.72

 הראשון

0.68

 continúas

0.67

 getFirst

0.66

 EVER

0.66

 pertama

0.66

Activations Density 0.345%

references to specific events or details related to time and recognition

No Comments

No Known Activations