INDEX

Explanations

terms related to hair and its characteristics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

}),

-0.85

ctuaries

-0.83

UMBUS

-0.81

 Schenk

-0.78

 suprême

-0.77

RDS

-0.76

 Arend

-0.75

 '.')

-0.74

 Enzo

-0.74

MockBean

-0.74

POSITIVE LOGITS

 hair

1.63

 HAIR

1.50

 Hair

1.50

Hair

1.42

HAIR

1.38

hair

1.31

haired

1.10

 haired

1.06

 hairs

1.05

 hairst

0.95

Activations Density 0.061%

terms related to hair and its characteristics

No Comments

No Known Activations