INDEX

Explanations

numerical and statistical data or references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 ModelExpression

-0.87

 كومونز

-0.81

 للاسماء

-0.80

GEBURTSDATUM

-0.79

 الحره

-0.79

addCriterion

-0.78



-0.76

delwed

-0.76

SBATCH

-0.76

Personendaten

-0.76

POSITIVE LOGITS

ništvo

0.38

man

0.38

</b>

0.38

djangoproject

0.37

 downward

0.37

 isSet

0.37

 Rück

0.36

but

0.36

Activations Density 1.000%

numerical and statistical data or references

No Comments

No Known Activations