INDEX

Explanations

differences and variations between subjects or items being discussed

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

fix

-0.44

 Bande

-0.42

Esp

-0.40

Esp

-0.40

nloa

-0.38

Lur

-0.37

ession

-0.37

badger

-0.37

 jovens

-0.37

 pass

-0.37

POSITIVE LOGITS

 differences

1.14

 Differences

1.10

Differences

1.02

AnchorStyles

0.98

 DIFFER

0.95

Differ

0.93

 مشين

0.93

differences

0.93

 difference

0.93

bedaan

0.93

Activations Density 0.707%

differences and variations between subjects or items being discussed

No Comments

No Known Activations