INDEX

Explanations

elements related to film categories and attributes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

StoryboardSegue

-0.96

SequentialGroup

-0.92

ReusableCell

-0.81

 InputDecoration

-0.77

 consultato

-0.77

 GenerationType

-0.73

tvguidetime

-0.72

migrationBuilder

-0.72

 مرئيه

-0.71

SharedCtor

-0.71

POSITIVE LOGITS

ẵn

0.48

 elettrica

0.39

ReadOnly

0.39

 automática

0.39

 affaires

0.38

脚注の使い方

0.37

 automático

0.36

IsRequired

0.36

 eléctrica

0.36

ậm

0.36

Activations Density 1.321%

elements related to film categories and attributes

No Comments

No Known Activations