INDEX

Explanations

letters or characters that may represent various categories or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

 Aven

-0.69

 venti

-0.69

ZZZZ

-0.66

 divid

-0.63

hamb

-0.63

 Schwe

-0.63

lemb

-0.63

ví

-0.61

 Senti

-0.61

ulti

-0.61

POSITIVE LOGITS

Przypisy

1.28

 AssemblyCulture

0.93

Viitteet

0.92

MigrationBuilder

0.91

IBar

0.85

 sherds

0.84

 Silurian

0.83

seamnă

0.81

 său

0.80

 commerciaux

0.79

Activations Density 0.946%

letters or characters that may represent various categories or classifications

No Comments

No Known Activations