INDEX

Explanations

terms related to historical events and geographic locations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

脚注の使い方

-0.76

SharedCtor

-0.75

 المعيارى

-0.75

MessageTagHelper

-0.73

 EINVAL

-0.68

@[+][

-0.68

ThroughAttribute

-0.64

RefreshLayout

-0.63

 MaterialApp

-0.59

AfterViewInit

-0.59

POSITIVE LOGITS

 occupied

1.32

 inhabited

1.09

 frequented

0.99

 populated

0.97

 Occupied

0.94

 visited

0.93

occupied

0.93

 unoccupied

0.92

 ocupado

0.85

 overrun

0.83

Activations Density 0.494%

terms related to historical events and geographic locations

No Comments

No Known Activations