INDEX

Explanations

negative statements and expressions of doubt regarding opinions, parties, and entities

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



-0.78

featureID

-0.75

RenderAtEndOf

-0.72

 AssemblyCulture

-0.70

IndentedString

-0.69

 ujednoznacz

-0.68

 propOrder

-0.68

 ligiloj

-0.68

 beginnetje

-0.67

IsMutable

-0.67

POSITIVE LOGITS

 none

0.67

 nenhum

0.58

 nadie

0.58

 ninguno

0.58

none

0.57

 nobody

0.57

 ninguém

0.56

 None

0.55

 ninguna

0.54

 żad

0.54

Activations Density 0.262%

negative statements and expressions of doubt regarding opinions, parties, and entities

No Comments

No Known Activations