INDEX

Explanations

access modifiers and their usage in code

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

Code-related keywords and context

np_acts-logits-general · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

 betweenstory

-0.92

PyExc

-0.73

InjectAttribute

-0.71

ſelben

-0.71

parsedMessage

-0.69

 Italijani

-0.69

featureID

-0.68

 Signalez

-0.68

enablog

-0.68

 Italijanski

-0.67

POSITIVE LOGITS

int

0.42

 String

0.41

int

0.41

String

0.37

 string

0.36

 bool

0.35

 thing

0.33

 struct

0.32

 different

0.31

 double

0.30

Activations Density 0.127%

access modifiers and their usage in code

Code-related keywords and context

No Comments

No Known Activations