INDEX

Explanations

HTML tags and formatting elements 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 @ 6-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.hook_mlp_out

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

</i>

-0.81

</em>

-0.77

annica

-0.65

</h6>

-0.57

 precisione

-0.52

</s>

-0.50

providedIn

-0.50

ünstler

-0.50

Архівовано

-0.49

جوايز

-0.49

POSITIVE LOGITS

انيف

0.72

featureID

0.70

 مرئيه

0.65

JsonHelper

0.64

IntoConstraints

0.63

SequentialGroup

0.55

reportWebVitals

0.55

 LoggerFactory

0.55

ValueStyle

0.54

CloseOperation

0.53

Activations Density 0.105%

HTML tags and formatting elements in the text

No Comments

No Known Activations