INDEX

Explanations

technical terms related to commands and performance metrics in engineering contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

endphp

-0.47

السكان

-0.43

RectangleBorder

-0.37

sidemargin

-0.35

Distribuzione

-0.35

specialchars

-0.35

Біографія

-0.35

 Shorts

-0.34

SharedCtor

-0.34

detectChanges

-0.34

POSITIVE LOGITS

 target

0.62

 goal

0.59

 desired

0.57

target

0.56

 desire

0.55

 goals

0.51

Goal

0.50

Target

0.50

 targets

0.49

 menging

0.49

Activations Density 0.093%

technical terms related to commands and performance metrics in engineering contexts

No Comments

No Known Activations