INDEX

Explanations

terms related to programming and technical processes

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

 nahilalakip

-1.10

'}>

-1.09

 XNUMX

-1.01

'])){

-0.94

'){

-0.91

ousand

-0.91

parsedMessage

-0.91

endence

-0.90

"){

-0.88

Rhestr

-0.87

POSITIVE LOGITS

 Champs

0.93

httphttps

0.85

 Bucs

0.83

 Atty

0.80

QUADS

0.77

 meds

0.76

 تانيه

0.75

Eqn

0.74

 GONNA

0.73

 Pollut

0.73

Activations Density 0.748%

terms related to programming and technical processes

No Comments

No Known Activations