INDEX

Explanations

links and navigation elements within a document

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 تانيه

-0.84

AndEndTag

-0.81

extAlignment

-0.79

tvguidetime

-0.77

 Autorisations

-0.73

ArgsConstructor

-0.73

 يتيمه

-0.70

Биография

-0.69

queryInterface

-0.68

Hochspringen

-0.67

POSITIVE LOGITS

 Link

1.07

Link

1.04

 href

1.04

 link

1.00

 LINK

0.93

AnchorTagHelper

0.91

link

0.90

NavLink

0.88

 links

0.86

LINK

0.84

Activations Density 0.037%

links and navigation elements within a document

No Comments

No Known Activations