INDEX

Explanations

technical terms and references related to algorithms and computational processes

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

-0.70

 iſt

-0.65

</caption>

-0.65

).\\

-0.63

etera

-0.62

 MessageBoxIcon

-0.61

 ſever

-0.59

 cetera

-0.59

?\\

-0.58

 ་་

-0.58

POSITIVE LOGITS

ppl

1.03

abt

0.92

0.86

lyk

0.85

cuz

0.83

frm

0.81

luv

0.78

thx

0.78

Pls

0.78

plz

0.76

Activations Density 0.305%

technical terms and references related to algorithms and computational processes

No Comments

No Known Activations