INDEX

Explanations

references to specific individuals or names in a narrative context

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

Appearing before relative pronouns

np_acts-logits-general · gemini-2.0-flash

clauses following punctuation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

rungsseite

-0.79

 ſind

-0.72

zzleHttp

-0.69

WithIOException

-0.66

ніципалі

-0.65

 disambiguazione

-0.65

 estekak

-0.63

ScopeManager

-0.63

تقاوى

-0.62

帖最后由

-0.62

POSITIVE LOGITS

who

0.76

 which

0.74

the

0.72

aka

0.72

 whose

0.70

 selaku

0.67

an

0.63

0.62

whose

0.61

ซึ่ง

0.57

Activations Density 0.498%

references to specific individuals or names in a narrative context

Appearing before relative pronouns

clauses following punctuation

No Comments

No Known Activations