INDEX

Explanations

frequently mentioned common practices or techniques in various contexts

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

 EconPapers

-0.63

octanol

-0.61

permitAll

-0.61

Biografi

-0.60

 kasarigan

-0.58

czegóły

-0.57

docx

-0.55

worfen

-0.54

QMetaType

-0.54

 gyhoeddwyd

-0.52

POSITIVE LOGITS

 commonly

1.12

 Commonly

1.05

popular

1.03

 popular

1.01

commonly

1.00

 brukar

0.90

ยม

0.88

 souvent

0.87

 often

0.86

 häufig

0.84

Activations Density 0.561%

frequently mentioned common practices or techniques in various contexts

No Comments

No Known Activations