INDEX

Explanations

references to governmental or organizational entities

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

 lenker

-0.77

CppMethod

-0.74

WireFormatLite

-0.72

Datuak

-0.60

 بيها

-0.57

 CreateTagHelper

-0.57

DotNetBar

-0.56

FunctionFlags

-0.54

ᅠ

-0.53

ABV

-0.53

POSITIVE LOGITS

ata

0.88

 ministry

0.80

 championship

0.77

ATA

0.74

 Ministry

0.68

mû

0.66

Ministry

0.65

 Championship

0.64

 remarque

0.64

 quoque

0.64

Activations Density 0.078%

references to governmental or organizational entities

No Comments

No Known Activations