INDEX

Explanations

negative expressions related to existence and absence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

gameserver

-0.52

TestBed

-0.52

 referenties

-0.49

hmig

-0.46

 Henri

-0.45

ftes

-0.45

ponge

-0.44

googleapis

-0.44

ldre

-0.43

Ngb

-0.42

POSITIVE LOGITS

 arşivlendi

0.87

않

0.87

 않았

0.81

 يتيمه

0.76

 <=",

0.76

 оригіналу

0.73

(!__

0.73

олові

0.73

دانشنامهٔ

0.72

elemField

0.72

Activations Density 0.229%

negative expressions related to existence and absence

No Comments

No Known Activations