INDEX

Explanations

technical terms and identifiers related to programming and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 vuotta

-0.47

 pungkasnya

-0.47

 kautta

-0.46

\}\\

-0.45

AccessorTable

-0.44

будь

-0.43

 travaillons

-0.42

রা

-0.42

บ้าง

-0.41

toHaveBeenCalled

-0.41

POSITIVE LOGITS

 AssemblyCulture

0.89

parsedMessage

0.71

colgroup

0.66

ⓧ

0.62

 HasFactory

0.61

itinéraire

0.60

 lenker

0.59

новниш

0.59

 Италијани

0.59

__.__

0.59

Activations Density 1.020%

technical terms and identifiers related to programming and data structures

No Comments

No Known Activations