INDEX

Explanations

references to specific names, locations, and scientific terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 Watkins

-0.97

اشته

-0.80

 erop

-0.79

Tow

-0.78

 Taft

-0.76

 Clifton

-0.75

ably

-0.75

 McClure

-0.73

Wat

-0.72

FLA

-0.70

POSITIVE LOGITS

 Czer

0.93

getColumnIndex

0.87

 FormsModule

0.84

otechnology

0.82

 Prit

0.81

 للمعارف

0.80

 Sicily

0.80

 Chant

0.80

 Biele

0.79

 Moss

0.78

Activations Density 2.122%

references to specific names, locations, and scientific terms

No Comments

No Known Activations