INDEX

Explanations

references to causality and violation of rules or expectations

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

Follows prepositions or punctuation

np_acts-logits-general · gemini-2.0-flash

pronouns and names

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 يتيمه

-1.03

}$

-0.84

 Normdatei

-0.82

 تانيه

-0.79

 estekak

-0.72

 tfsi

-0.72

tserrat

-0.71

manjaro

-0.70

 cdti

-0.68

êques

-0.68

POSITIVE LOGITS

her

1.31

she

1.15

his

1.13

him

1.01

he

0.99

 their

0.92

 they

0.83

She

0.83

He

0.81

she

0.79

Activations Density 3.943%

references to causality and violation of rules or expectations

Follows prepositions or punctuation

pronouns and names

No Comments

No Known Activations