INDEX

Explanations

names of individuals or entities involved in legal or medical contexts

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

AsUp

-0.52

ſelves

-0.52

StructEnd

-0.49

 pleaſure

-0.48

writeFieldEnd

-0.47

InputTagHelper

-0.46

 greateſt

-0.45

 leaſt

-0.45

 createSprite

-0.44

 itſelf

-0.42

POSITIVE LOGITS

imedes

0.47

HostException

0.47

 Poul

0.47

 Annapolis

0.45

PARIS

0.45

Amsterdam

0.45

 Rockville

0.45

Ong

0.45

 محفوظة

0.44

Ong

0.44

Activations Density 0.346%

names of individuals or entities involved in legal or medical contexts

No Comments

No Known Activations