INDEX

Explanations

legal or mathematical symbols and citations of publications

oai_token-act-pair · gemini-2.0-flash

special characters and formatting elements

np_token-act-pair-logits · gpt-4o-mini

Code snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵↵↵

-1.73

</h3>

-0.71

↵↵↵↵↵

-0.68

↵↵↵↵↵↵

-0.66

↵↵↵↵↵↵↵

-0.65

</em>

-0.61

↵↵↵↵↵↵↵↵↵

-0.60

</i>

-0.59

↵↵↵↵

-0.59

</h5>

-0.59

POSITIVE LOGITS

RectangleBorder

0.71

̈́

0.70

 snippetHide

0.63

出版年

0.61

خواندن

0.61

`),

0.61

Rhestr

0.60

Amicalement

0.59

ihnachten

0.59

 beginnetje

0.57

Activations Density 4.969%

legal or mathematical symbols and citations of publications

special characters and formatting elements

Code snippets

No Comments

No Known Activations