INDEX

Explanations

references to volumes and editions of academic publications

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

StrictEqual

-0.48

 ivelany

-0.46

 cauſe

-0.45

 vastaan

-0.44

 caufe

-0.44

 pymongo

-0.40

 ſta

-0.40

 Democrá

-0.39

 reaſon

-0.39

Ợ

-0.39

POSITIVE LOGITS

XXX

0.81

jsii

0.78

XXX

0.77

XL

0.77

uxxxx

0.74

aarrggbb

0.73

xxx

0.73

XL

0.72

xxx

0.69

liv

0.68

Activations Density 0.284%

references to volumes and editions of academic publications

No Comments

No Known Activations