INDEX

Explanations

words ending in "ator", "ate", "rel", "ard", "slave", "interational" or "ayan"

oai_token-act-pair · gemini-2.0-flash

"-ator" and "-ate" suffixes

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 ktorí

-0.72

 kteří

-0.71

 którzy

-0.70

 folks

-0.60

 people

-0.60

 themselves

-0.58

 ambao

-0.53

 quienes

-0.50

 their

-0.50

 members

-0.49

POSITIVE LOGITS

 ModelExpression

0.76

 AssemblyProduct

0.74

 Roskov

0.73

 autorytatywna

0.72

 aapt

0.71

 Numerade

0.69

SequentialGroup

0.67

 grandchild

0.66

 CreateTagHelper

0.65

 незавершена

0.65

Activations Density 0.742%

words ending in "ator", "ate", "rel", "ard", "slave", "interational" or "ayan"

"-ator" and "-ate" suffixes

No Comments

No Known Activations