INDEX

Explanations

terms related to the prefix "un" and various associated concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/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.21.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

 الرياضيه

-0.63

Personendaten

-0.62

 lenker

-0.60

хьтан

-0.58

 snippetHide

-0.57

KommentareTeilen

-0.56

ffindor

-0.55

 للمعارف

-0.54

 Мексичка

-0.54

 Escolar

-0.52

POSITIVE LOGITS

Un

0.63

 uncon

0.54

Un

0.52

 incom

0.52

 uncontrollable

0.52

 incon

0.50

 unhas

0.50

Uns

0.49

 unbound

0.49

 unidentified

0.48

Activations Density 0.773%

terms related to the prefix "un" and various associated concepts

No Comments

No Known Activations