INDEX

Explanations

html code and URLs

oai_token-act-pair · gemini-2.0-flash

code and markup

np_max-act-logits · gemini-2.0-flash

=

np_max-act-logits · gpt-5-mini Triggered by @chenshw0109

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 English

-0.82

Efq

-0.78

expandindo

-0.74

\{\\

-0.73

ValueStyle

-0.73

AddTagHelper

-0.72

IUrlHelper

-0.71

 OFDb

-0.71

TypedDataSet

-0.68

Autoritní

-0.68

POSITIVE LOGITS

<bos>

0.66

rxjs

0.48

minecraft

0.44

JAKARTA

0.44

IGraphics

0.44

roek

0.42

 africaine

0.42

 catatan

0.42

 ferons

0.42

 africain

0.41

Activations Density 8.294%

html code and URLs

code and markup

=

No Comments

No Known Activations