INDEX

Explanations

programming terminology and structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

rungsseite

-0.88

 مشين

-0.87

adaptiveStyles

-0.86

 propOrder

-0.86

webElementXpaths

-0.81

ⓧ

-0.80

setVerticalGroup

-0.77

 autorytatywna

-0.73

SourceChecksum

-0.72

oneofs

-0.72

POSITIVE LOGITS

 فريبيس

0.54

parseDouble

0.47

<eos>

0.45

setContentView

0.41

Footnotes

0.41

0.39

 dimaksud

0.38

hasMany

0.37

mappedBy

0.36

0.35

Activations Density 0.015%

programming terminology and structure

No Comments

No Known Activations