INDEX

Explanations

references to loading and saving models in programming contexts

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

performance or speed

np_acts-logits-general · gemini-2.0-flash

speed and performance

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

:✨

-0.61

 puissiez

-0.57

AttributeSet

-0.53

Personensuche

-0.52

 aceptas

-0.52

legel

-0.47

 putty

-0.46

éez

-0.46

 vested

-0.45

맞

-0.45

POSITIVE LOGITS

 speed

1.01

CPU

0.89

 performance

0.89

speed

0.89

 speeding

0.86

performance

0.85

cpu

0.81

slow

0.79

Speed

0.79

 slow

0.78

Activations Density 1.262%

references to loading and saving models in programming contexts

performance or speed

speed and performance

No Comments

No Known Activations