INDEX

Explanations

specific programming and computer science terminology, particularly related to methods, classes, and data handling

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

Code-related tokens after specific words

np_acts-logits-general · gemini-2.0-flash

property or parameter names

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ValueStyle

-0.68

 ब्रेकडाउन

-0.63

AnchorStyles

-0.62

ActionCreators

-0.57

AxisAlignment

-0.56

 BoxFit

-0.56

IBOutlet

-0.55

*/),

-0.54

omitempty

-0.53

 CreateTagHelper

-0.52

POSITIVE LOGITS

Geografi

0.48

icylic

0.45

otation

0.44

↵↵↵

0.44

 Evangelio

0.43

 policy

0.43

äjä

0.43

<eos>

0.42

 publication

0.42

 material

0.41

Activations Density 0.216%

specific programming and computer science terminology, particularly related to methods, classes, and data handling

Code-related tokens after specific words

property or parameter names

No Comments

No Known Activations

specific programming and computer science terminology, particularly related to methods, classes, and data handling

Code-related tokens after specific words

property or parameter names

No Comments

No Known Activations