INDEX

Explanations

references to academic publishers and locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

ScopeManager

-0.52

asana

-0.49

RSpec

-0.45

chließ

-0.45

OGND

-0.44

Inno

-0.42

AccessorTable

-0.41

 Fest

-0.41

 هوا

-0.41

naming

-0.40

POSITIVE LOGITS

 Publishing

1.03

 Press

1.03

 publishing

0.98

 Publishers

0.97

 publishers

0.96

Press

0.91

 press

0.90

 yayınları

0.82

 publisher

0.81

PUBLISH

0.80

Activations Density 0.179%

references to academic publishers and locations

No Comments

No Known Activations