INDEX

Explanations

punctuation and formatting markers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

ientôt

-0.56

ogast

-0.54

 stanov

-0.52

omod

-0.52

 femininas

-0.52

 useEffect

-0.51

ष्य

-0.50

 falsas

-0.50

 originais

-0.49

様々

-0.48

POSITIVE LOGITS

Overall

0.89

 Overall

0.87

 overall

0.81

RenderAtEndOf

0.76

overall

0.73

 Compared

0.69

Positives

0.69

 Insgesamt

0.68

Compared

0.65

Negatives

0.65

Activations Density 0.149%

punctuation and formatting markers

No Comments

No Known Activations