INDEX

Explanations

references to specific people or characters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.37.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

 obvious

-0.49

 officer

-0.48

 ось

-0.47

 orange

-0.45

 orang

-0.42

 optical

-0.42

 organza

-0.41

 optics

-0.40

 officers

-0.39

Karakteristik

-0.39

POSITIVE LOGITS

JspWriter

0.55

Hauptartikel

0.54

 saites

0.53

 typelib

0.52

Hochspringen

0.51

hoeddwyd

0.49

Tazama

0.49

lahoma

0.47

rungsseite

0.47

Activations Density 0.935%

references to specific people or characters

No Comments

No Known Activations