INDEX

Explanations

syntax related to code structure and operations

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

Characters appearing in code or formulas

np_acts-logits-general · gemini-2.0-flash

equations or mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 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

-0.70

-0.68

-0.67

-0.66

-0.65

-0.62

-0.61

POSITIVE LOGITS

 néz

0.87

 történ

0.82

 intermédiaire

0.79

 grecque

0.79

 esetben

0.77

 définiti

0.77

 quelcon

0.77

 rempliss

0.76

 avulla

0.75

 csal

0.75

Activations Density 0.911%

syntax related to code structure and operations

Characters appearing in code or formulas

equations or mathematical expressions

No Comments

No Known Activations