INDEX

Explanations

phrases indicating legal processes and actions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 tenda

-0.41

ngths

-0.39

 Atenas

-0.38

 tendance

-0.36

Dieu

-0.35

 rechange

-0.35

-0.34

omy

-0.33

</strong>

-0.33

POSITIVE LOGITS

ThroughAttribute

1.11

initComponents

1.04

GEBURTSDATUM

0.96

SourceChecksum

0.96

 BoxDecoration

0.90

MultipartFile

0.88

^(@)

0.87

aarrggbb

0.87

PerformLayout

0.86

WriteBarrier

0.84

Activations Density 0.609%

phrases indicating legal processes and actions

No Comments

No Known Activations