INDEX

Explanations

references to applications and their contexts

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ítulo

-0.53

 opening

-0.51

 stand

-0.50

 open

-0.49

 Goodwin

-0.47

angal

-0.45

far

-0.44

 minimo

-0.43

 andato

-0.43

▼

-0.43

POSITIVE LOGITS

app

1.00

 getApp

0.87

App

0.84

 linkovi

0.84

InstrumentedTest

0.78

ImageContext

0.76

ftagPool

0.76

JSP

0.75

 ویکی‌پدی

0.74

 Appreciation

0.74

Activations Density 0.211%

references to applications and their contexts

No Comments

No Known Activations