INDEX

Explanations

references to the pronoun "he" and its variations along with related scientific terms or elements

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

"He" followed by citations or brackets

np_acts-logits-general · gemini-2.0-flash

Heisenberg and related words

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

aarrggbb

-0.63

 للاسماء

-0.61

:✨

-0.53

الإنجليزية

-0.52

off

-0.51

 Chip

-0.50

CreateModel

-0.46

 habido

-0.46

لينكات

-0.46

 pulito

-0.46

POSITIVE LOGITS

 <<<<<<<<<<<<<<

0.71

()?;

0.69

 Majefty

0.68

"]);

0.68

ResumeLayout

0.66

 defaultstate

0.66

lioz

0.66

Hek

0.64

=$((

0.64

adecimal

0.63

Activations Density 0.156%

references to the pronoun "he" and its variations along with related scientific terms or elements

"He" followed by citations or brackets

Heisenberg and related words

No Comments

No Known Activations