INDEX

Explanations

specific character sequences in code and text formatting

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

Tokens followed by numbers or specific letters

np_acts-logits-general · gemini-2.0-flash

hexadecimal codes and abbreviations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 TableColumn

-0.76

жника

-0.72

quelize

-0.72

 مُعرِّف

-0.71

 DriverManager

-0.68

Referensi

-0.67

ize

-0.66

aarrggbb

-0.66

Squares

-0.65

жник

-0.65

POSITIVE LOGITS

ting

0.99

thet

0.93

tttt

0.90

tt

0.89

ttt

0.86

 Otta

0.85

tott

0.80

ts

0.78

0.76

tait

0.75

Activations Density 1.486%

specific character sequences in code and text formatting

Tokens followed by numbers or specific letters

hexadecimal codes and abbreviations

No Comments

No Known Activations