INDEX

Explanations

specific programming terms and elements related to data structures and functions

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

Tokens within parentheses or brackets

np_acts-logits-general · gemini-2.0-flash

advance_backward, module, MODE, call

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

"])

-0.58

"]);

-0.55

imp

-0.53

/******/

-0.52

teln

-0.52

orney

-0.51

ANCIAL

-0.51

FORMAN

-0.49

 năng

-0.49

"],

-0.48

POSITIVE LOGITS

 الرياضيه

0.73

IntoConstraints

0.67

 hjäl

0.66

:+:

0.62

 Allí

0.57

extAlignment

0.56

 xenia

0.56

 itſelf

0.56

 Molière

0.55

 Abbé

0.55

Activations Density 1.346%

specific programming terms and elements related to data structures and functions

Tokens within parentheses or brackets

advance_backward, module, MODE, call

No Comments

No Known Activations