INDEX

Explanations

terms related to measurements and comparisons in scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 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

 AssemblyProduct

-0.60

ConstraintMaker

-0.53

ButterKnife

-0.51

ArrowToggle

-0.51

UrlResolution

-0.50

 насељу

-0.48

basicConfig

-0.47

ActionCreators

-0.47

 فريبيس

-0.46

DIPSETTING

-0.46

POSITIVE LOGITS

 mention

0.39

 interpreter

0.39

 того

0.37

 incorporation

0.36

ABUL

0.35

언

0.35

 dolphins

0.35

 inclusion

0.35

 reference

0.35

aleza

0.34

Activations Density 1.003%

terms related to measurements and comparisons in scientific contexts

No Comments

No Known Activations