INDEX

Explanations

technical terms and acronyms related to computing or programming environments

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

────────

-0.83

 ་་

-0.78

鈥

-0.74

 armen

-0.72

───

-0.72

ագրություններ

-0.72

 ―――――

-0.71

———

-0.70

 pyplot

-0.70

URIS

-0.70

POSITIVE LOGITS

लिए

0.83

voyez

0.82

팎

0.81

IsMutable

0.81

 antaranya

0.80

 beliau

0.75

 Begründung

0.73

 culoare

0.73

iaceae

0.72

บ้าง

0.71

Activations Density 1.299%

technical terms and acronyms related to computing or programming environments

No Comments

No Known Activations