INDEX

Explanations

key pronouns and references to individuals involved in legal or personal narratives

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

bria

-0.44

ficult

-0.44

polation

-0.41

risti

-0.41

ähren

-0.41

hot

-0.41

thouse

-0.41

EDOM

-0.40

 termin

-0.40

 itself

-0.39

POSITIVE LOGITS

 Lordship

0.79

fjspx

0.78

 lordship

0.76

makeConstraints

0.75

 समीक्षक

0.74

httphttps

0.72

 Профиль

0.67

Schriften

0.66

 typelib

0.66

ineno

0.65

Activations Density 0.453%

key pronouns and references to individuals involved in legal or personal narratives

No Comments

No Known Activations