INDEX

Explanations

specific programming or technical terms commonly associated with coding errors and directory paths

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

Code snippets and abbreviations

np_acts-logits-general · gemini-2.0-flash

CETP sequence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 strength

-0.89

strength

-0.82

 STRENGTH

-0.78

 Strength

-0.77

Strength

-0.75

STRENGTH

-0.62

 streng

-0.57

gwt

-0.56

 strengths

-0.56

]]

-0.55

POSITIVE LOGITS

 الاطلاع

0.60

 Jefus

0.59

行政区划

0.57

يكب

0.57

 AssemblyProduct

0.56

 itſelf

0.55

RenderAtEndOf

0.53

 Мексичка

0.53

الحياه

0.53

RegistryLite

0.52

Activations Density 0.308%

specific programming or technical terms commonly associated with coding errors and directory paths

Code snippets and abbreviations

CETP sequence

No Comments

No Known Activations