INDEX

Explanations

references to scientific terminology and research-related metrics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/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.19.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

 AssemblyCulture

-0.90

 disponibilités

-0.90

uliert

-0.76

Datuak

-0.75

Hozzáférés

-0.75

+#+#

-0.74

'">

-0.73

ური

-0.72

Identyfik

-0.71

ագրություններ

-0.69

POSITIVE LOGITS

 Rask

0.64

0.62

 ràng

0.60

 Rous

0.59

Ril

0.56

0.55

 Rica

0.55

RMA

0.55

ربای

0.54

rpc

0.53

Activations Density 1.602%

references to scientific terminology and research-related metrics

No Comments

No Known Activations