INDEX

Explanations

instances of the word "new" across various contexts

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

 however

-0.55

 Aether

-0.54

 kasi

-0.51

 traveler

-0.50

 traveller

-0.48

 Essa

-0.48

meck

-0.47

 postIndex

-0.47

 unfortunately

-0.47

Traveler

-0.47

POSITIVE LOGITS

migrationBuilder

1.09

")));

0.92

 }}"></

0.89

"]);

0.88

AddTagHelper

0.85

 IBOutlet

0.84

typeparam

0.83

HasForeignKey

0.83

"]));

0.83

new

0.82

Activations Density 0.035%

instances of the word "new" across various contexts

No Comments

No Known Activations