INDEX

Explanations

sections and references to algorithms and estimators in a structured format

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ArgsConstructor

-0.77

 <<<<<<<<<<<<<<

-0.73

下载附件

-0.72

writeField

-0.70

 يتيمه

-0.70

tagHelperRunner

-0.68

]";

-0.67

Portály

-0.67

andidaten

-0.67

."));

-0.67

POSITIVE LOGITS

↵↵

0.55

WithIOException

0.51

 parecen

0.46

 otomatig

0.45

 EconPapers

0.45

 referenties

0.44

InitStruct

0.43

 impianti

0.43

 suaminya

0.43

škin

0.42

Activations Density 0.567%

sections and references to algorithms and estimators in a structured format

No Comments

No Known Activations