INDEX

Explanations

references to mathematical variables and parameters related to sets and algorithms

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

Архівовано

-0.50

 ModelAndView

-0.46

 TextAppearance

-0.43

blum

-0.40

interopRequire

-0.40

 singular

-0.40

下载附件

-0.40

EndContext

-0.40

azen

-0.39

 trouw

-0.38

POSITIVE LOGITS

 HasFactory

0.47

 GenerationType

0.44

Morfo

0.41

Хро

0.40

⟬

0.39

ähteet

0.39

oneofs

0.38

oredCriteria

0.38

 Redaktion

0.38

 inspiradoras

0.36

Activations Density 0.061%

references to mathematical variables and parameters related to sets and algorithms

No Comments

No Known Activations