INDEX

Explanations

terms related to advanced computational concepts and performance improvements in technology

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

Pfalz

-0.47

 actionMode

-0.47

])]

-0.47

alleries

-0.46

 AssemblyCompany

-0.45

 médicas

-0.45

 Paglinawan

-0.45

wikkeld

-0.44

moire

-0.44

Ech

-0.44

POSITIVE LOGITS

 constraint

0.93

 optimization

0.92

 constraints

0.91

 optim

0.82

 objective

0.81

 Constraints

0.80

 Constraint

0.79

 optimisation

0.78

 resourceCulture

0.78

 Optimization

0.78

Activations Density 0.808%

terms related to advanced computational concepts and performance improvements in technology

No Comments

No Known Activations