INDEX

Explanations

technical language related to scientific research and methodologies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 ddelweddau

-0.73

MLLoader

-0.70

󠁢

-0.69

ModelAdmin

-0.64

帖最后由

-0.64

AutoSize

-0.63

WithFormat

-0.63

NOPQRST

-0.60

ագրություններ

-0.59

enumi

-0.58

POSITIVE LOGITS

 chrétiens

0.66

 dieux

0.62

berdayakan

0.59

 prêtres

0.59

 épaules

0.58

 âmes

0.57

 nélk

0.57

$.

0.57

 états

0.57

.}~\

0.57

Activations Density 1.102%

technical language related to scientific research and methodologies

No Comments

No Known Activations