INDEX

Explanations

terms related to data analysis and assessment 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

Puss

-0.48

fated

-0.44

intro

-0.43

Unsubscribe

-0.43

ӑ

-0.41

例句

-0.40

 wikihow

-0.40

unto

-0.40

емо

-0.39

 Emig

-0.39

POSITIVE LOGITS

ThroughAttribute

0.77

tagHelperRunner

0.75

 Paglinawan

0.67

(!__

0.66

 Administrativna

0.62

WriteTagHelper

0.61

}],

0.61

 AssemblyCulture

0.61

 BorderRadius

0.61

 Fische

0.61

Activations Density 0.667%

terms related to data analysis and assessment in various contexts

No Comments

No Known Activations