INDEX

Explanations

references to scientific principles or theories

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

TagMode

-0.92

principalTable

-0.92

Demografia

-0.74

 BIBSYS

-0.71

ंदीखरीदारी

-0.71

 defaultstate

-0.71

WriteTagHelper

-0.70

 صوتيه

-0.69

DockStyle

-0.66

 समीक्षक

-0.62

POSITIVE LOGITS

 Their

0.58

but

0.56

He

0.52

His

0.51

and

0.51

 never

0.51

Their

0.49

거

0.49

It

0.49

 ادار

0.48

Activations Density 0.325%

references to scientific principles or theories

No Comments

No Known Activations