INDEX

Explanations

references to a root element or object in a structured data context

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

httphttps

-0.84

MIDDLEWARE

-0.80

 Chamb

-0.79

 Lari

-0.74

thodon

-0.74

żeli

-0.72

 Belvedere

-0.72

SDC

-0.71

verwijspagina

-0.70

 fibrillation

-0.70

POSITIVE LOGITS

 Root

1.98

 root

1.97

 ROOT

1.91

 roots

1.83

ROOT

1.81

root

1.80

 Roots

1.77

Root

1.76

Roots

1.67

roots

1.67

Activations Density 0.062%

references to a root element or object in a structured data context

No Comments

No Known Activations