INDEX

Explanations

references to articles or reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

ness

-0.82

PerformLayout

-0.79

Hauptartikel

-0.78

```

-0.76

zzlies

-0.74

,-\

-0.73

thenReturn

-0.73

})-\

-0.72

HAEL

-0.71

NESS

-0.71

POSITIVE LOGITS

 articles

1.62

 article

1.42

 Article

1.41

 Articles

1.40

 ARTICLE

1.37

Articles

1.35

Article

1.35

ARTICLE

1.33

articles

1.31

article

1.28

Activations Density 0.042%

references to articles or reports

No Comments

No Known Activations