INDEX

Explanations

structure and format elements in code snippets

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

Code-related keywords or delimiters

np_acts-logits-general · gemini-2.0-flash

code blocks and keywords

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 Goss

-0.86

 Merz

-0.79

jScrollPane

-0.77

ecap

-0.77

CreateMap

-0.77

UserScript

-0.76

 Marcell

-0.76

KTP

-0.75

RequestMapping

-0.75

formKey

-0.75

POSITIVE LOGITS

1.10

RenderAtEndOf

0.91

0.90

 Alves

0.77

:✨

0.73

 SEDS

0.69

iarkan

0.67

 Wikispecies

0.65

توان

0.64

Activations Density 0.162%

structure and format elements in code snippets

Code-related keywords or delimiters

code blocks and keywords

No Comments

No Known Activations