INDEX

Explanations

programming-related keywords, specifically those related to class definitions, methods, and overrides

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

 bero

-0.46

UNIDENTIFIED

-0.46

AndEndTag

-0.45

ਭ

-0.44

endo

-0.43

bkz

-0.43

spin

-0.43

sk

-0.42

 jueces

-0.42

DoubleQuotes

-0.42

POSITIVE LOGITS

 صوتيه

0.70

例文帳に追加

0.69

SequentialGroup

0.68

 typelib

0.67

parsedMessage

0.63

 تضيفلها

0.61

verwijspagina

0.60

principalTable

0.59

bonnet

0.59

complexContent

0.58

Activations Density 0.183%

programming-related keywords, specifically those related to class definitions, methods, and overrides

No Comments

No Known Activations