INDEX

Explanations

function definitions and method calls in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 nasional

-0.48

hammad

-0.46

料

-0.46

yit

-0.45

افظة

-0.45

OUGHT

-0.44

}{*}{}

-0.44

tief

-0.44

aree

-0.44

 مرئيه

-0.43

POSITIVE LOGITS

tvguidetime

0.79

 surla

0.70

SuccessListener

0.70

SharedDtor

0.66

StoreMessageInfo

0.65

CompleteListener

0.64

Tē

0.62

انجليز

0.59

mainen

0.59

曖昧さ回避

0.58

Activations Density 0.381%

function definitions and method calls in code

No Comments

No Known Activations