INDEX

Explanations

occurrences of conjunctions and phrases that indicate sequences or connections in the text

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

Followed by uppercase letters

np_acts-logits-general · gemini-2.0-flash

General William

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

acken

-0.63

Xna

-0.59

 estimés

-0.57

 photolibrary

-0.56

InvalidProtocol

-0.56

Климат

-0.56

 nawr

-0.54

catchError

-0.53

 Esprit

-0.53

'>

-0.53

POSITIVE LOGITS

如下

0.74

 inside

0.62

 referencing

0.57

WireFormatLite

0.56

 확인

0.55

 default

0.55

 manually

0.55

 somewhere

0.54

 "..\..\..\

0.54

IBOutlet

0.54

Activations Density 0.980%

occurrences of conjunctions and phrases that indicate sequences or connections in the text

Followed by uppercase letters

General William

No Comments

No Known Activations