INDEX

Explanations

programming-related keywords and terms

oai_token-act-pair · gpt-4o-mini Triggered by @bot

Code, names, or titles

np_acts-logits-general · gemini-2.0-flash

archaic English spellings

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

+#+#

-0.76

-0.72

SupportActionBar

-0.70

WebElementEntity

-0.70

 estimés

-0.69

-0.68

endphp

-0.66

#+#

-0.65

 NSCoder

-0.64

POSITIVE LOGITS

 myſelf

1.21

 themſelves

1.07

 himſelf

1.06

 doubtnut

1.05

 purpoſe

1.00

 Monfieur

1.00

 ſeveral

0.99

Efq

0.99

 Theſe

0.96

 pleaſure

0.96

Activations Density 0.612%

programming-related keywords and terms

Code, names, or titles

archaic English spellings

No Comments

No Known Activations