INDEX

Explanations

abbreviations or acronyms related to medical or scientific terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

Cyfeiriadau

-0.71

पया

-0.65

 صوتيه

-0.61

versiti

-0.57

érias

-0.56

 Zapo

-0.55

 taba

-0.55

 Cinta

-0.54

="@+

-0.54

 Schweitzer

-0.54

POSITIVE LOGITS

expandindo

0.58

μφωνα

0.57

 dirait

0.56

+:+

0.55

 endforeach

0.55

PhysRevD

0.55

 doInBackground

0.55

 AssemblyCulture

0.54

 Durchsch

0.53

Activations Density 0.345%

abbreviations or acronyms related to medical or scientific terms

No Comments

No Known Activations