INDEX

Explanations

complex mathematical expressions and relationships involving variables and indices

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

Code snippets with increment operators

np_acts-logits-general · gemini-2.0-flash

programming code and math notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

减

-0.74

 reduction

-0.73

减

-0.72

Minus

-0.71

 minus

-0.71

 reductions

-0.69

Subtract

-0.66

 Reduction

-0.66

減

-0.66

 Minus

-0.64

POSITIVE LOGITS

posedge

0.82

enumii

0.77

MigrationBuilder

0.74

 disponibilités

0.73

клопе

0.71

WebVitals

0.71

AddTagHelper

0.70

devamını

0.68

PreferredItem

0.65

++

0.65

Activations Density 0.240%

complex mathematical expressions and relationships involving variables and indices

Code snippets with increment operators

programming code and math notation

No Comments

No Known Activations