INDEX

Explanations

the word "Am" and its variations, indicating a focus on personal identity or state of being

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

AddTagHelper

-0.83

 بيها

-0.61

iecie

-0.59

webElementXpaths

-0.58

 SEDS

-0.57

Autoritní

-0.57

 fubject

-0.57

 magasiner

-0.56

 oprot

-0.55

Panamoan

-0.55

POSITIVE LOGITS

Lähteet

0.56

 tekem

0.52

am

0.52

Am

0.48

assination

0.47

ctis

0.46

 häufigsten

0.46

 AssemblyCulture

0.46

ฏิ

0.44

 vostri

0.44

Activations Density 0.072%

the word "Am" and its variations, indicating a focus on personal identity or state of being

No Comments

No Known Activations