INDEX

Explanations

numerical data or statistical information

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

Text after question marks ("Q:")

np_acts-logits-general · gemini-2.0-flash

html tags and punctuation

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

脚注の使い方

-0.96

^(@)

-0.91

Externí

-0.88

IntoConstraints

-0.85

 للمعارف

-0.84

MigrationBuilder

-0.83

 IndexPath

-0.82

írus

-0.80

IANGLES

-0.79

 disambiguazione

-0.79

POSITIVE LOGITS

↵

1.39

</blockquote>

1.29

↵↵

1.23

↵↵↵

1.16

</h1>

1.05

↵↵↵↵

1.04

<eos>

1.00

</b>

0.97

↵↵↵↵↵

0.97

</strong>

0.97

Activations Density 2.522%

numerical data or statistical information

Text after question marks ("Q:")

html tags and punctuation

No Comments

No Known Activations