INDEX

Explanations

specific numerical codes or identifiers associated with datasets or research studies

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BagConstraints

-0.66

 SIMBAD

-0.62

 AssemblyTitle

-0.61

setof

-0.60

 leksikon

-0.59

 Embal

-0.58

 مشين

-0.58

gie

-0.58

Efq

-0.57

IntentFilter

-0.57

POSITIVE LOGITS

-------

0.56

Pyx

0.52

ագրություններ

0.52

azzjoni

0.50

 фирмы

0.50

nos

0.49

ikar

0.49

ITOS

0.48

لينكات

0.48

 lesz

0.47

Activations Density 0.047%

specific numerical codes or identifiers associated with datasets or research studies

No Comments

No Known Activations