INDEX

Explanations

mathematical symbols and formatting related to matrices and statistical notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

TResult

-0.87

 Pais

-0.80

ificantly

-0.77

LikeLike

-0.76

FormState

-0.76

invokeLater

-0.75

biter

-0.75

 Autorizaciones

-0.73

NECT

-0.73

Rui

-0.72

POSITIVE LOGITS

Hat

1.76

hat

1.67

 hats

1.65

HAT

1.65

Hat

1.62

hat

1.61

 Hats

1.43

HAT

1.41

Hats

1.26

hats

1.26

Activations Density 0.141%

mathematical symbols and formatting related to matrices and statistical notation

No Comments

No Known Activations