INDEX

Explanations

references to brushes and brain-related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

GLS

-0.84

ArgsConstructor

-0.83

 Lakeside

-0.78

 Tides

-0.77

 Akufo

-0.77

 Hoyt

-0.73

 Udaipur

-0.72

ذت

-0.72

 WaitForSeconds

-0.72

 Napole

-0.71

POSITIVE LOGITS

BR

1.04

Br

0.99

 brush

0.95

br

0.94

 brushes

0.93

Bri

0.92

Bra

0.91

 Brind

0.89

 Brush

0.89

Br

0.88

Activations Density 0.073%

references to brushes and brain-related terms

No Comments

No Known Activations