INDEX

Explanations

technical terms and functions related to programming and APIs

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

Code snippets with special characters

np_acts-logits-general · gemini-2.0-flash

closing braces and symbols

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

↵

-0.86

-0.73

<eos>

-0.68

↵↵↵

-0.67

↵↵↵↵↵

-0.60

</blockquote>

-0.59

-0.58

”

-0.54

POSITIVE LOGITS

IntoConstraints

1.06

AndEndTag

0.94

 كومونز

0.91

=",

0.90

 MainAxisSize

0.90

:",

0.90

&,

0.89

}",

0.88

\%,

0.88

 ↓,

0.88

Activations Density 0.387%

technical terms and functions related to programming and APIs

Code snippets with special characters

closing braces and symbols

No Comments

No Known Activations