INDEX

Explanations

references to identity and its variations within texts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Geſ

-0.63

 Monfieur

-0.63

Eſ

-0.52

 pleaſure

-0.51

 gethan

-0.50

 newData

-0.49

 ſou

-0.48

 Füße

-0.48

 paſſ

-0.47

 financière

-0.46

POSITIVE LOGITS

 identity

1.05

 Identity

0.93

identity

0.93

Identity

0.90

 identities

0.87

 IDENTITY

0.85

 Identities

0.76

IDENTITY

0.69

got

0.66

 clone

0.66

Activations Density 0.436%

references to identity and its variations within texts

No Comments

No Known Activations