INDEX

Explanations

terms related to electrical circuits and their components

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

DataBinding

-0.51

 Cabot

-0.51

 Zacks

-0.46

unhofer

-0.45

ittarius

-0.45

ucchini

-0.44

 acesta

-0.44

AnchorStyles

-0.43

 Staub

-0.43

 Callable

-0.43

POSITIVE LOGITS

uxxxx

0.70

✨:

0.66

findpost

0.66

 Waray

0.63

 EClass

0.59

bootstrapcdn

0.58

 exciter

0.58

 PyLong

0.58

PWM

0.57

OGND

0.56

Activations Density 0.370%

terms related to electrical circuits and their components

No Comments

No Known Activations