INDEX

Explanations

questions related to opinion and belief

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

 Majefty

-0.65

 doInBackground

-0.62

\"");

-0.60

енча

-0.60

ⓧ

-0.57

expandindo

-0.56

 CanadaChoose

-0.56

 Reſ

-0.54

eavor

-0.54

 smtplib

-0.54

POSITIVE LOGITS

ibouti

0.58

AnchorStyles

0.56

Manbalar

0.56

 juridiques

0.56

isContained

0.53

QMetaType

0.52

chaun

0.51

 velkommen

0.50

ArgsConstructor

0.49

InSection

0.49

Activations Density 0.214%

questions related to opinion and belief

No Comments

No Known Activations