INDEX

Explanations

names of companies and organizations, particularly those that include "Ltd."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Wissens

-0.60

γε

-0.58

sigs

-0.56

 Лег

-0.56

artiges

-0.55

 Wight

-0.54

smithy

-0.53

ddagger

-0.52

teto

-0.52

PerformLayout

-0.50

POSITIVE LOGITS

providedIn

0.97

 stakeholders

0.77

Ltd

0.76

 cref

0.73

 moschino

0.73

ltd

0.69

Efq

0.68

VersionUID

0.68

 Pergamon

0.65

Activations Density 0.049%

names of companies and organizations, particularly those that include "Ltd."

No Comments

No Known Activations