INDEX

Explanations

references to objects and their attributes in a technical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.0.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

RenderAtEndOf

-0.90

Scénario

-0.75

 архивлан

-0.69

RegressionTest

-0.64

avond

-0.60

 Ibid

-0.58

CppMethod

-0.57

offsetof

-0.55

 løpet

-0.54

綢

-0.54

POSITIVE LOGITS

NameInMap

0.91

Commerce

0.72

بوابة

0.69

Objects

0.66

 iconTwitter

0.66

Portale

0.63

Personensuche

0.62

 Riet

0.62

Datuak

0.62

 doInBackground

0.61

Activations Density 0.026%

references to objects and their attributes in a technical context

No Comments

No Known Activations