INDEX

Explanations

possessive pronouns indicating ownership or association

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

Possessive pronouns

np_acts-logits-general · gemini-2.0-flash

phrases indicating possession

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

затор

-0.43

].

-0.43

 Besch

-0.42

-0.41

↵↵

-0.40

inis

-0.40

他才

-0.40

otta

-0.40

POSITIVE LOGITS

Datuak

0.96

 distanciation

0.91

ſelf

0.89

rungsseite

0.89

StructEnd

0.86

 GenerationType

0.85

 wits

0.84

 XCTest

0.83

ScopeManager

0.82

ſelves

0.76

Activations Density 0.220%

possessive pronouns indicating ownership or association

Possessive pronouns

phrases indicating possession

No Comments

No Known Activations