INDEX

Explanations

statistics and comparisons

oai_token-act-pair · gemini-2.0-flash

unusual or uncommon words

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

Statistics/Numbers

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tagHelperRunner

-0.67

 وتسجيلات

-0.65

itology

-0.63

 AssemblyCompany

-0.62

cshtml

-0.60

GraphicsUnit

-0.56

httphttps

-0.56

 useState

-0.54

 cụ

-0.54

AddTagHelper

-0.53

POSITIVE LOGITS

örgy

0.51

Koordinaten

0.51

ItemBackground

0.50

siasme

0.48

osoba

0.47

hatic

0.47

 propOrder

0.47

avaş

0.46

oczes

0.45

 fallu

0.45

Activations Density 1.940%

statistics and comparisons

unusual or uncommon words

Statistics/Numbers

No Comments

No Known Activations