INDEX

Explanations

references to code configuration parameters in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 unknownFields

-0.66

脚注の使い方

-0.56

 Investig

-0.52

shadowOpacity

-0.51

tahui

-0.48

LLocation

-0.48

kre

-0.48

Glej

-0.48

plor

-0.47

 adult

-0.47

POSITIVE LOGITS

NameInMap

0.64

igshid

0.50

findpost

0.48

kloped

0.48

ScopeManager

0.46

 Picchu

0.46

bram

0.46

roek

0.46

typeorm

0.46

bata

0.46

Activations Density 0.310%

references to code configuration parameters in a programming context

No Comments

No Known Activations