INDEX

Explanations

questions and uncertainties regarding clarity or understanding of concepts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ineno

-0.61

 séparation

-0.49

 تانيه

-0.49

rollable

-0.48

 fièvre

-0.46

ilever

-0.44

ResumeLayout

-0.43

orithmic

-0.43

ligent

-0.43

 répartition

-0.43

POSITIVE LOGITS

تقاوى

0.71

GrantedAuthority

0.69

interopRequire

0.65

новништво

0.64

 useContext

0.59

://$

0.59

DOCTYPE

0.57

]")]

0.57

出版年

0.56

 BoxDecoration

0.54

Activations Density 0.490%

questions and uncertainties regarding clarity or understanding of concepts

No Comments

No Known Activations