INDEX

Explanations

technical terms and measurements related to particle physics experiments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 ***!

-0.85

 '\\;'

-0.60

NewGuid

-0.58

исленность

-0.57

 LoggerFactory

-0.54

WebServlet

-0.51

çalves

-0.51

getColumnIndex

-0.51

IndentedString

-0.50

 protoimpl

-0.50

POSITIVE LOGITS

fit

0.86

 uncertainties

0.85

 fits

0.83

 fitting

0.77

 Uncertain

0.76

 quoted

0.76

 estimate

0.74

 fitted

0.73

 Fitting

0.71

 Fits

0.71

Activations Density 1.960%

technical terms and measurements related to particle physics experiments

No Comments

No Known Activations