INDEX

Explanations

technical terms related to programming and device management

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

BagConstraints

-0.41

 vectorielles

-0.40

 Ambiental

-0.39

 enfans

-0.36

 fumée

-0.35

 škoda

-0.35

colgroup

-0.35

principalTable

-0.35

catraz

-0.35

Protocol

-0.34

POSITIVE LOGITS

LookAnd

0.55

 linkovi

0.52

原始内容存档于

0.48



0.47

身の

0.46

ismet

0.46

SourceChecksum

0.45

身

0.43

jspb

0.43

DMETHOD

0.42

Activations Density 0.143%

technical terms related to programming and device management

No Comments

No Known Activations