INDEX

Explanations

technical terms and method-related keywords in programming or software documentation

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

adaptiveStyles

-0.84

AccessorTable

-0.62

 للاسماء

-0.62

Seeder

-0.55

encodeWith

-0.55

下载附件

-0.54

 betweenstory

-0.53

UniformLocation

-0.53

 EconPapers

-0.53

Бахар

-0.52

POSITIVE LOGITS

ьаж

0.66

 виправивши

0.65

 censiti

0.65

 VIDEOTAPE

0.64

 jsPsych

0.58

 FetchType

0.58

깥

0.56

 חיצוניים

0.55

mappedBy

0.55

enterOuterAlt

0.55

Activations Density 0.333%

technical terms and method-related keywords in programming or software documentation

No Comments

No Known Activations