INDEX

Explanations

references to funding and support in academic or research contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/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.17.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

 hlavy

-0.78

 pleaſure

-0.72

 vlasy

-0.72

 Monfieur

-0.71

ateľ

-0.70

 vzduchu

-0.70

 będziesz

-0.70

 Anſ

-0.65

 faſt

-0.65

 gwaran

-0.65

POSITIVE LOGITS

UseVisualStyle

0.68

„

0.57

GEBURTSDATUM

0.55

цездатний

0.52

pl

0.52

Prague

0.49

 pstmt

0.49

„

0.49

 Michal

0.48

RefreshLayout

0.48

Activations Density 0.036%

references to funding and support in academic or research contexts

No Comments

No Known Activations