INDEX

Explanations

technical terms and variables related to programming or software development

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PerformLayout

-0.73

arted

-0.73

abestanden

-0.62

клопе

-0.60

 насељу

-0.60

adpleegd

-0.60

CloseOperation

-0.60

 hemi

-0.59

vanced

-0.58

Portály

-0.58

POSITIVE LOGITS

 facie

0.70

FIM

0.59

ürnberg

0.58

Efq

0.57

WhereInput

0.56

token

0.55

 Barna

0.55

=="

0.54

Sabrina

0.54

راهيم

0.54

Activations Density 0.030%

technical terms and variables related to programming or software development

No Comments

No Known Activations