INDEX

Explanations

references to information and its underlying significance

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

 Monfieur

-0.69

askins

-0.65

mybatisplus

-0.63

دانشنامهٔ

-0.61

 silenzio

-0.60

 surla

-0.59

 themſelves

-0.58

zysta

-0.58

 indisponible

-0.58

 indruk

-0.58

POSITIVE LOGITS

 connotations

0.66

 implications

0.65

 mengandung

0.64

 nuances

0.64

 connotation

0.62

 CreateTagHelper

0.60

 nuance

0.58

 ContentValues

0.57

 contain

0.57

 MessageBoxIcon

0.57

Activations Density 0.471%

references to information and its underlying significance

No Comments

No Known Activations