INDEX

Explanations

mathematical terms and symbols commonly used in statistical and mathematical models

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 Reactivity

-0.52

 SDLK

-0.51

ไม้

-0.46

 lame

-0.44

 Kombat

-0.44

 beat

-0.43

 bril

-0.42

atih

-0.42

ện

-0.42

beat

-0.42

POSITIVE LOGITS

 distribution

1.28

 distributions

1.16

 distributed

1.13

 Distribution

1.13

distribution

1.06

 DISTRIBUTION

1.05

Distribution

1.04

 distribute

1.03

 Distributions

0.99

 distribución

0.98

Activations Density 0.983%

mathematical terms and symbols commonly used in statistical and mathematical models

No Comments

No Known Activations