INDEX

Explanations

specific terms related to data, analysis, and technical parameters in research 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

$_['

-0.49

 Exacts

-0.44

Cop

-0.43

Ming

-0.43

groups

-0.41

 Ming

-0.41

inker

-0.41

 evolved

-0.41

core

-0.40

 مق

-0.40

POSITIVE LOGITS

RegressionTest

0.52

 mijne

0.46

ErrUnexpectedEOF

0.46

 vicenda

0.45

 persoons

0.45

 skjer

0.44

tableFuture

0.44

addContainerGap

0.42

bý

0.42

 příjem

0.42

Activations Density 0.274%

specific terms related to data, analysis, and technical parameters in research contexts

No Comments

No Known Activations