INDEX

Explanations

terms and names related to historical or legislative events, particularly in relation to significant agreements and their contexts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

 newArr

-0.84

انيف

-0.80

CURLOPT

-0.80

schra

-0.78

 Gentry

-0.78

lceil

-0.77

quini

-0.77

 SOCK

-0.76

 Huss

-0.75

PathVariable

-0.74

POSITIVE LOGITS

 Kalis

0.71

россий

0.67

 Spie

0.66

dmg

0.66

 Bianca

0.64

Rost

0.64

FLU

0.63

 Kanna

0.63

endaftaran

0.62

 cancer

0.61

Activations Density 7.084%

terms and names related to historical or legislative events, particularly in relation to significant agreements and their contexts

No Comments

No Known Activations