INDEX

Explanations

quantitative data or statistics presented in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

parsedMessage

-1.09

PerformLayout

-1.03

ViewFeatures

-0.95

NameInMap

-0.95

 otomatig

-0.93

 defaultstate

-0.89

WriteTagHelper

-0.89

awaiter

-0.88

Personendaten

-0.88

 bezeichneter

-0.86

POSITIVE LOGITS

 Barbier

0.58

 publics

0.53

 Hartman

0.49

 tủ

0.48

 Palestina

0.47

 Italiana

0.47

 figliu

0.46

 peggio

0.44

 Audiodateien

0.44

 colombiana

0.44

Activations Density 0.722%

quantitative data or statistics presented in the text

No Comments

No Known Activations