INDEX

Explanations

references to silicon and related elements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

 للمعارف

-0.87

 Aristi

-0.81

piecze

-0.79

 Judea

-0.78

Uda

-0.77

 wanda

-0.76

 Kome

-0.75

 bezeichneter

-0.74

Identyfik

-0.73

 Kono

-0.72

POSITIVE LOGITS

Si

1.59

Si

1.49

si

1.41

si

1.38

SI

1.26

SI

1.21

 Siro

1.09

Sir

1.07

SIR

1.04

 Siva

0.98

Activations Density 0.101%

references to silicon and related elements

No Comments

No Known Activations