INDEX

Explanations

numerical data and specific outcomes from results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/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.10.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

migrationBuilder

-0.70

 kasarigan

-0.59

 חיצוניים

-0.55

 defaultstate

-0.54

 pulumi

-0.50

parsedMessage

-0.49

AntiForgeryToken

-0.47

EDEFAULT

-0.47

וויק

-0.46

VIAF

-0.46

POSITIVE LOGITS

Datuak

0.73

 MainAxisSize

0.71

 fédé

0.64

 diarrhoea

0.62

 subgoal

0.62

HttpFoundation

0.61

 Chicano

0.60

 ciudadana

0.58

 stessa

0.57

blick

0.57

Activations Density 0.077%

numerical data and specific outcomes from results

No Comments

No Known Activations