INDEX

Explanations

references to skills based on specific categories

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

Followed by indefinite articles ("a", "an", etc.)

np_acts-logits-general · gemini-2.0-flash

: a / an

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

 betweenstory

-0.90

AndEndTag

-0.88

 protoimpl

-0.87

jooq

-0.81

AddTagHelper

-0.76

 Jefus

-0.75

Efq

-0.75

alnız

-0.75

ArrowToggle

-0.75

Personendaten

-0.74

POSITIVE LOGITS

2.27

an

1.83

 sebuah

1.13

 eine

1.08

 einem

1.07

 seorang

1.03

een

1.03

 another

1.02

一个

1.02

 một

1.01

Activations Density 0.696%

references to skills based on specific categories

Followed by indefinite articles ("a", "an", etc.)

: a / an

No Comments

No Known Activations