INDEX

Explanations

closing braces and HTML tags

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

Code snippets or code-related items

np_acts-logits-general · gemini-2.0-flash

when conventional methods

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

And

-0.45

-0.44

↵↵

-0.43

-0.42

jer

-0.41

ref

-0.41

 live

-0.41

iel

-0.41

avis

-0.41

POSITIVE LOGITS

 Normdatei

0.93

AndEndTag

0.91

IntoConstraints

0.86

 viewDidLoad

0.82

 مشين

0.82

ьаж

0.79

 pinulongan

0.73

 estekak

0.73

ⓧ

0.72

ंदीखरीदारी

0.71

Activations Density 0.061%

closing braces and HTML tags

Code snippets or code-related items

when conventional methods

No Comments

No Known Activations