INDEX

Explanations

special formatting markers or code-like structures in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 similarly

-0.77

 Similarly

-0.64

 Prior

-0.61

 likewise

-0.58

 prior

-0.57

Similarly

-0.57

 Additionally

-0.56

fsch

-0.56

gi

-0.55

 regardless

-0.53

POSITIVE LOGITS

expandindo

0.95

')")

0.79

 مشين

0.78

Great

0.76

CodeAttribute

0.75

 للاسماء

0.75

}));

0.74

Nice

0.72

Worlds

0.71

 eccell

0.71

Activations Density 0.009%

special formatting markers or code-like structures in the text

No Comments

No Known Activations