INDEX

Explanations

references to literature, particularly in a bibliographic context

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ValueStyle

-0.93

 تضيفلها

-0.86

 Pickett

-0.85

SBATCH

-0.82



-0.77

ený

-0.75

 Kobayashi

-0.75

endphp

-0.74

ecap

-0.74

 Constance

-0.73

POSITIVE LOGITS

Literature

1.18

 Literature

1.16

Lit

1.05

 Liter

1.05

 literature

1.03

Lit

1.02

 LITERATURE

1.00

Liter

0.97

literature

0.97

 LITER

0.95

Activations Density 0.165%

references to literature, particularly in a bibliographic context

No Comments

No Known Activations