INDEX

Explanations

references to pairs of individuals or entities in a relationship or collaboration

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

ArrowToggle

-0.53

Хьажоргаш

-0.53

://

-0.50

principalTable

-0.48

ously

-0.45

どき

-0.44

HIRE

-0.44

ậm

-0.44

entait

-0.43

 kolei

-0.43

POSITIVE LOGITS

'][]

0.70

}")]

0.66

 twain

0.66

Together

0.64

 together

0.64

ImageContext

0.64

 myſelf

0.62

AutoField

0.61

يكب

0.60

 Together

0.60

Activations Density 0.445%

references to pairs of individuals or entities in a relationship or collaboration

No Comments

No Known Activations