INDEX

Explanations

specific references to scientific citations and their structural details

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

️

-0.60

ävän

-0.58

 Schulter

-0.56

بخ

-0.53

uldron

-0.53

baikan

-0.52

Piv

-0.52

postalCode

-0.52

jpeg

-0.50

 Bourgoin

-0.50

POSITIVE LOGITS

StructEnd

0.89

ttk

0.88

YY

0.82

PPS

0.80

BeforeAll

0.77

vv

0.76

HH

0.74

 Nunn

0.72

ymm

0.72

rrggbb

0.70

Activations Density 1.645%

specific references to scientific citations and their structural details

No Comments

No Known Activations