INDEX

Explanations

references to specific formatting or coding structures

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

Text within square brackets and parentheses

np_acts-logits-general · gemini-2.0-flash

inline citations `[@...`

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

Vidite

-0.94

 endblock

-0.83

oredCriteria

-0.75

Datuak

-0.74

InsertCommand

-0.74

 flesta

-0.74

IUrlHelper

-0.73

RegistryLite

-0.73

Autoritní

-0.71

 يتيمه

-0.71

POSITIVE LOGITS

texttt

0.49

出版年

0.48

cdnjs

0.44

leston

0.43

Leaders

0.42

ătă

0.42

tention

0.40

 mathvariant

0.40

("\

0.40

"\

0.39

Activations Density 1.101%

references to specific formatting or coding structures

Text within square brackets and parentheses

inline citations `[@...`

No Comments

No Known Activations