INDEX

Explanations

information related to subjects and their identities in scientific studies or legal contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

SequentialGroup

-0.93

RegressionTest

-0.52

出版年

-0.48

 jerawat

-0.46

ImageContext

-0.44

DoubleQuotes

-0.44

mişti

-0.42

thodoxy

-0.42

Stub

-0.41

ativní

-0.41

POSITIVE LOGITS

 >=",

0.70

jsdelivr

0.68

 betweenstory

0.64

onAttach

0.62

principalTable

0.62

 فريبيس

0.61

Efq

0.61

 Monfieur

0.60

 Majefty

0.60

 smtplib

0.59

Activations Density 0.402%

information related to subjects and their identities in scientific studies or legal contexts

No Comments

No Known Activations