INDEX

Explanations

references to academic institutions and publications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 kaarangay

-0.71

 AssemblyTitle

-0.56

处

-0.51

<bos>

-0.50

Composable

-0.47

 internetowa

-0.47

 makl

-0.46

 puissiez

-0.46

處

-0.45

「

-0.45

POSITIVE LOGITS

ReusableCell

1.10

ScopeManager

1.00

Hauptartikel

0.87

::~

0.85

#+#

0.84

+#+

0.84

 keras

0.80

 PublicKey

0.77

keras

0.76

 disambiguazione

0.74

Activations Density 0.106%

references to academic institutions and publications

No Comments

No Known Activations