INDEX

Explanations

references to characters and their relationships in narratives

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

seamnă

-0.72

 Arund

-0.59

 række

-0.54

thora

-0.54

setBorder

-0.53

 vektör

-0.53

Anu

-0.51

 internazionali

-0.51

 Nant

-0.49

 Tolu

-0.49

POSITIVE LOGITS

 himself

1.88

his

1.75

himself

1.66

his

1.46

he

1.42

him

1.41

 Himself

1.31

His

1.23

彼は

1.20

 seinem

1.19

Activations Density 0.266%

references to characters and their relationships in narratives

No Comments

No Known Activations