INDEX

Explanations

references to critical or negative evaluations of projects or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

makeText

-0.69

 smtplib

-0.49

脚注の使い方

-0.48

Abitanti

-0.46

Significance

-0.45

'{@

-0.45

[]:

-0.45

setScene

-0.43

my

-0.43

ess

-0.43

POSITIVE LOGITS

 nào

0.75

 spared

0.70

HostException

0.61

RegressionTest

0.59

 تانيه

0.58

 anyone

0.58

 anybody

0.57

TestingModule

0.57

 sparing

0.57

GraphicsUnit

0.56

Activations Density 0.152%

references to critical or negative evaluations of projects or events

No Comments

No Known Activations