INDEX

Explanations

terms related to associations and relationships between entities or concepts

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

 pratiques

-0.50

ménage

-0.50

rubin

-0.50

 utilitarian

-0.48

icho

-0.48

__["

-0.47

 Practical

-0.47

 vela

-0.47

 praktisch

-0.47

 combinado

-0.46

POSITIVE LOGITS

providedIn

0.82

الإنجليزية

0.78

 disambiguazione

0.77

InstrumentedTest

0.77

NewUrlParser

0.76

 beginnetje

0.75

LookAnd

0.70

AccessorTable

0.69

帖最后由

0.68

 doInBackground

0.68

Activations Density 0.096%

terms related to associations and relationships between entities or concepts

No Comments

No Known Activations