INDEX

Explanations

phrases that indicate social interactions or character relationships

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

after capitalized names/titles

np_acts-logits-general · gemini-2.0-flash

The Hobbit and Lord of the Rings

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

TemporalType

-0.62

verwijspagina

-0.59

 Ptolemy

-0.57

 BoxFit

-0.54

LookAnd

-0.54

 Crimean

-0.54

 targets

-0.53

 Crimea

-0.53

rungsseite

-0.52

 Solano

-0.52

POSITIVE LOGITS

 hobbit

0.96

 Tolkien

0.93

 Hobbit

0.93

olkien

0.81

 Gandalf

0.79

 Rings

0.72

 Shire

0.71

Rings

0.69

andalf

0.68

hob

0.62

Activations Density 0.054%

phrases that indicate social interactions or character relationships

after capitalized names/titles

The Hobbit and Lord of the Rings

No Comments

No Known Activations