INDEX

Explanations

mathematical notation and parameters

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

INTO

-0.57

 oubli

-0.56

 tryck

-0.56

 bloquer

-0.55

enterian

-0.55

 techniczne

-0.54

')}}

-0.53

holdet

-0.53

 küm

-0.53

 merve

-0.53

POSITIVE LOGITS

 lenker

1.08

 Vlas

0.96

AnchorStyles

0.92

tvguidetime

0.92

AddTagHelper

0.88

richTextPanel

0.88

 تضيفلها

0.86

ImageContext

0.86

ReusableCell

0.81

argout

0.80

Activations Density 0.321%

mathematical notation and parameters

No Comments

No Known Activations