INDEX

Explanations

references to properties, types, or characteristics in a technical or academic context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k

Configuration

google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.hook_mlp_out

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

 '\\;'

-0.80

zzlement

-0.78

Personensuche

-0.75

 inquest

-0.72

InstrumentedTest

-0.69

AsUp

-0.68

-0.66

MethodManager

-0.64

expandindo

-0.63

-0.62

POSITIVE LOGITS

tagHelperRunner

0.58

 ReSharper

0.57

berdayakan

0.57

posób

0.56

seamnă

0.55

ſelves

0.52

thinkable

0.50

ьаж

0.49

 saját

0.49

 abstrait

0.46

Activations Density 0.212%

references to properties, types, or characteristics in a technical or academic context

No Comments

No Known Activations