INDEX

Explanations

technical terms and concepts related to scientific approximations and models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

NewGuid

-0.72

Населення

-0.66

ьаж

-0.65

 }}"></

-0.59

+#+

-0.57

 '\\;'

-0.57

 clearColor

-0.56

stret

-0.55

EndProject

-0.54

Obrázky

-0.53

POSITIVE LOGITS

 approximations

0.67

 approximation

0.64

 predicting

0.62

 approximates

0.60

 approximate

0.56

 prediction

0.55

 predict

0.53

 approximating

0.53

 simplistic

0.52

 assumptions

0.52

Activations Density 1.270%

technical terms and concepts related to scientific approximations and models

No Comments

No Known Activations