INDEX

Explanations

references to individuals and their roles or actions

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

GEBURTSDATUM

-0.85

تقاوى

-0.80

tvguidetime

-0.72

InputBorder

-0.72

OGND

-0.72

rungsseite

-0.69

 auroit

-0.68

 Verſ

-0.68

 Theodo

-0.68

cæ

-0.68

POSITIVE LOGITS

 also

1.25

 также

0.85

 następnie

0.81

also

0.76

 further

0.75

 then

0.74

 همچنین

0.74

 także

0.72

 також

0.71

 également

0.70

Activations Density 0.520%

references to individuals and their roles or actions

No Comments

No Known Activations