INDEX

Explanations

code snippets related to variable declaration and assignment

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

Code-related tokens, especially symbols and names

np_acts-logits-general · gemini-2.0-flash

code snippets and optional values

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

jah

-0.49

抱

-0.48

extAlignment

-0.47

zige

-0.43

 статистики

-0.43

مس

-0.42

 Stamps

-0.42

ूत

-0.41

vi

-0.41

metter

-0.41

POSITIVE LOGITS

 ModelExpression

1.03

aarrggbb

0.99

Nullable

0.95

EDEFAULT

0.91

 possibly

0.90

may

0.88

InjectAttribute

0.87

 GenerationType

0.86

 maybe

0.85

 Maybe

0.82

Activations Density 0.221%

code snippets related to variable declaration and assignment

Code-related tokens, especially symbols and names

code snippets and optional values

No Comments

No Known Activations