INDEX

Explanations

proper nouns, particularly names of people, places, and significant terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

httphttps

-0.57

󠁢

-0.48

RenderAtEndOf

-0.47

Geplaatst

-0.47

 nakalista

-0.46

Vegeu

-0.43

 nikt

-0.42

مصادر

-0.42

ReadInt

-0.42

 laikā

-0.42

POSITIVE LOGITS

})`

0.45

SES

0.44

 monop

0.44

 petro

0.43

 malnutrition

0.43

 Cassette

0.43

 PlayStation

0.42

 Cinema

0.42

 psychotherapy

0.42

ſammen

0.41

Activations Density 3.042%

proper nouns, particularly names of people, places, and significant terms

No Comments

No Known Activations