INDEX

Explanations

mentions of software versions

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

IntoConstraints

-0.83

 InputDecoration

-0.79

 חיצוניים

-0.74

makeConstraints

-0.73

ulents

-0.73

çalves

-0.71

ratulations

-0.70

HCC

-0.69

 makeStyles

-0.68

utnik

-0.67

POSITIVE LOGITS

 VERSION

1.58

 Version

1.52

 versions

1.51

 version

1.50

Version

1.45

version

1.37

VERSION

1.35

 Versions

1.30

 getVersion

1.20

Versions

1.18

Activations Density 0.149%

mentions of software versions

No Comments

No Known Activations