INDEX

Explanations

references to statistical outcomes or results

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 surla

-0.98

PerformLayout

-0.93

fromnode

-0.84

 Италијани

-0.80

تقاوى

-0.78

 صوتيه

-0.77

цездатний

-0.77

kháu

-0.77

IntoConstraints

-0.75

GEBURTSDATUM

-0.75

POSITIVE LOGITS

↑

0.48

igny

0.46

enx

0.45

omentos

0.45

écnicas

0.45

raisemb

0.43

useum

0.43

gator

0.42

 Concepción

0.42

 lẽ

0.41

Activations Density 0.046%

references to statistical outcomes or results

No Comments

No Known Activations