INDEX

Explanations

terms related to retail, casting calls, and printed publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 leak

-0.51

 Flucht

-0.46

ometri

-0.45

 stránky

-0.45

lapi

-0.43

소

-0.42

 tetto

-0.42

énario

-0.41

 Utility

-0.41

 nhật

-0.41

POSITIVE LOGITS

 physically

1.04

 physical

0.97

 Physically

0.90

physical

0.90

Physical

0.85

 fís

0.82

 fisik

0.76

 Physical

0.74

PHYSICAL

0.73

 surla

0.73

Activations Density 0.703%

terms related to retail, casting calls, and printed publications

No Comments

No Known Activations