INDEX

Explanations

terms related to compensation and adjustments in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 dago

-0.48

 Finley

-0.48

 finas

-0.44

úst

-0.44

 basura

-0.42

 Guzmán

-0.42

 кӀ

-0.42

 Lawler

-0.41

Gep

-0.41

colazione

-0.41

POSITIVE LOGITS

 compensate

1.09

 compens

1.00

 compensating

0.95

 Compens

0.94

 compensation

0.94

 Compensation

0.91

 compensated

0.89

 compensatory

0.88

 AssemblyCulture

0.85

setVerticalGroup

0.85

Activations Density 0.267%

terms related to compensation and adjustments in various contexts

No Comments

No Known Activations