INDEX

Explanations

citation marks and references in text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

Personendaten

-1.09

makeText

-0.81

Tikang

-0.81

 Мексичка

-0.80

saraba

-0.79

ActionCreators

-0.79

Xna

-0.79

GEBURTS

-0.78

 createSprite

-0.76

 يتيمه

-0.75

POSITIVE LOGITS

↵

0.56

<eos>

0.53

↵↵

0.52

assertTrue

0.46

0.44

 referenties

0.42

št

0.39

）.

0.39

anglès

0.39

↵↵↵

0.39

Activations Density 0.077%

citation marks and references in text

No Comments

No Known Activations