INDEX

Explanations

phrases related to coding structures and definitions in programming contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 Ters

-0.60

 TAMBÉM

-0.59

DispatchToProps

-0.58

wnież

-0.57

etheless

-0.57

 Laplacian

-0.53

TintMode

-0.52

มาะ

-0.51

 Shaksp

-0.51

 Shakspeare

-0.51

POSITIVE LOGITS

 للمعارف

0.75

tagHelper

0.67

 समीक्षाओं

0.66

WriteLiteral

0.62

 EconPapers

0.61

enumi

0.59

<bos>

0.58

CodeAttribute

0.56

 Konferenz

0.54

ICE

0.52

Activations Density 0.226%

phrases related to coding structures and definitions in programming contexts

No Comments

No Known Activations