INDEX

Explanations

terms related to weighted calculations and parameters in mathematical expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

enumi

-0.62

帖最后由

-0.61

 belangrij

-0.55

jectures

-0.55

XtraReports

-0.53

RegressionTest

-0.53

TemporalType

-0.52

IImage

-0.51

psies

-0.51

UMBIA

-0.49

POSITIVE LOGITS

 FetchType

0.61

timeScale

0.59

Selection

0.55

 selection

0.55

 Selection

0.50

 Мексичка

0.50

Халык

0.49

ungsbedingungen

0.48

GetAxis

0.45

 operador

0.45

Activations Density 1.440%

terms related to weighted calculations and parameters in mathematical expressions

No Comments

No Known Activations