INDEX

Explanations

references to governmental and jurisdictional entities, particularly in relation to laws and public policy

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

ⓘ

-0.59

atimes

-0.54

types

-0.53

 calma

-0.49

类型的

-0.47

 hinaus

-0.47

งาม

-0.46

inh

-0.46

usters

-0.45

him

-0.45

POSITIVE LOGITS

LookAnd

0.84

Efq

0.81

 صوتيه

0.77

 protoimpl

0.76

TintMode

0.76

 myſelf

0.74

 Majefty

0.74

IntoConstraints

0.74

 كومونز

0.73

IUrlHelper

0.73

Activations Density 0.405%

references to governmental and jurisdictional entities, particularly in relation to laws and public policy

No Comments

No Known Activations