INDEX

Explanations

technical terms and methodologies related to scientific research and testing

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

selves

-0.70

צלחה

-0.66

 fatica

-0.61

thail

-0.61

entrion

-0.61

chafter

-0.60

impresa

-0.59

herself

-0.57

\"%

-0.57

 gyer

-0.57

POSITIVE LOGITS

Autoritní

0.64

Tw

0.64

Tw

0.61

httphttps

0.59

GEBURTSDATUM

0.59

complexContent

0.58

ims

0.56

 immersion

0.55

Aut

0.55

GroupLayout

0.55

Activations Density 2.010%

technical terms and methodologies related to scientific research and testing

No Comments

No Known Activations