INDEX

Explanations

references to methods, components, and code structures in programming

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-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

 BoxFit

-0.78

 <<<<<<<<<<<<<<

-0.75

 كومونز

-0.72

ftagPool

-0.71

 HasFactory

-0.69

RegressionTest

-0.69

expandindo

-0.68

 snippetHide

-0.65

StructEnd

-0.65

 ExecuteAsync

-0.64

POSITIVE LOGITS

IContainer

0.59

 Roskov

0.30

ResId

0.29

 encar

0.28

Vod

0.28

 competitivos

0.26

mapsto

0.26

 entrevista

0.25

 Corea

0.25

Nob

0.25

Activations Density 0.021%

references to methods, components, and code structures in programming

No Comments

No Known Activations