INDEX

Explanations

references to fibers and their properties or characteristics in various contexts

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-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

Azi

-0.56

 الرياضيه

-0.54

 magna

-0.49

 herz

-0.48

кипедия

-0.46

 Repr

-0.46

siębior

-0.46

wały

-0.45

pita

-0.45

Clear

-0.45

POSITIVE LOGITS

 fiber

0.93

DockStyle

0.89

 Fiber

0.85

 fibre

0.84

fiber

0.82

 fibres

0.79

Fiber

0.79

fibre

0.76

netbeans

0.75

 fibers

0.74

Activations Density 0.220%

references to fibers and their properties or characteristics in various contexts

No Comments

No Known Activations