INDEX

Explanations

specific numerical values, especially around data representation and software coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

 "..\..\..\

-0.86

 protoimpl

-0.83

RegressionTest

-0.83

EndInit

-0.80

ISupport

-0.78

 <<<<<<<<<<<<<<

-0.78

ThroughAttribute

-0.75

 "..\..\

-0.74

setVerticalGroup

-0.74

 typelib

-0.71

POSITIVE LOGITS

########.

0.71

 itſelf

0.69

nefs

0.59

 Мексичка

0.57

omalainen

0.56

.}~\

0.56

 lastname

0.56

ksessa

0.56

 mensuales

0.55

Activations Density 0.109%

specific numerical values, especially around data representation and software coding contexts

No Comments

No Known Activations