INDEX

Explanations

factors related to genetic variation and evolutionary processes

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

followed by an explanation

np_acts-logits-general · gemini-2.0-flash

explains or justifies patterns

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

Negative Logits

 Roskov

-0.71

 calldata

-0.67

TagMode

-0.66

 Bergh

-0.61

InjectAttribute

-0.60

MigrationBuilder

-0.59

orgung

-0.59

 становника

-0.58

principalColumn

-0.56

UVWXYZ

-0.53

POSITIVE LOGITS

 explanation

3.01

 explain

2.90

 explanations

2.76

 explaining

2.74

 explains

2.67

 explained

2.49

explain

2.43

explanation

2.40

 explica

2.29

 Explanation

2.22

Activations Density 0.882%

factors related to genetic variation and evolutionary processes

followed by an explanation

explains or justifies patterns

No Known Activations