INDEX

Explanations

repeated phrases or patterns that suggest ongoing actions or states

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

 hår

-0.71

fromCharCode

-0.70

 Merit

-0.68

 malattie

-0.63

 Vasco

-0.63

 lunghi

-0.61

 abbin

-0.61

 associative

-0.61

szönöm

-0.60

 hjär

-0.60

POSITIVE LOGITS

AsUp

0.87

/>\

0.80

)");

0.79

expandindo

0.77

".

0.76

$")

0.73

PreferredItem

0.73

")->

0.73

"]);

0.72

LabelTagHelper

0.71

Activations Density 0.053%

repeated phrases or patterns that suggest ongoing actions or states

No Comments

No Known Activations