INDEX

Explanations

references to prior works or sources cited in a document

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

styleUrls

-0.61

IsPostBack

-0.56

principalTable

-0.56

Aiheesta

-0.55

DAOImpl

-0.54

SuppressMessage

-0.51

 defaultstate

-0.50

CDU

-0.48

Applet

-0.48

"]));

-0.48

POSITIVE LOGITS

 reference

1.09

ValueStyle

1.00

 references

0.97

 pleaſure

0.81

 Monfieur

0.80

 trailing

0.76

ItemBackground

0.76

 riferimento

0.76

 purpoſe

0.75

 raiſ

0.74

Activations Density 0.093%

references to prior works or sources cited in a document

No Comments

No Known Activations