INDEX

Explanations

terms related to statistical estimation and modeling methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

setopt

-0.84

 getRule

-0.76

دیگر

-0.73

Ruh

-0.71

 Folge

-0.71

্ন

-0.69

konomi

-0.68

 коробка

-0.68

InstanceState

-0.67

angeran

-0.67

POSITIVE LOGITS

ting

1.38

ating

1.30

ging

1.29

izing

1.26

NING

1.19

ning

1.19

TING

1.18

cting

1.13

ING

1.10

gggg

1.10

Activations Density 1.478%

terms related to statistical estimation and modeling methodologies

No Comments

No Known Activations