INDEX

Explanations

numerical values and technical specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

 JpaRepository

-0.77

contentLoaded

-0.73

mybatisplus

-0.71

kloped

-0.65

writeFieldEnd

-0.64

 Taktlose

-0.64

UserScript

-0.63

MLLoader

-0.62

IsContent

-0.62

RenderAtEndOf

-0.62

POSITIVE LOGITS

 ejecutivo

0.39

 Romains

0.34

 Schönheit

0.33

IntoConstraints

0.32

 nocturno

0.31

 aclar

0.30

 ujar

0.30

 introducción

0.30

horabuena

0.30

 ansiedad

0.30

Activations Density 0.003%

numerical values and technical specifications

No Comments

No Known Activations