INDEX

Explanations

mentions of incorporation and things associated with companies

oai_token-act-pair · gemini-2.0-flash

variations of the word 'limited'

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

company names

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Photocase

-0.43

entie

-0.41

og

-0.40

 phát

-0.40

ILON

-0.39

 haystack

-0.39

inc

-0.39

 graça

-0.38

 frappe

-0.38

andro

-0.37

POSITIVE LOGITS

__":

0.81

 limitation

0.80

 Limited

0.78

Limited

0.77

 Limit

0.76

Limitation

0.76

 limitée

0.75

limited

0.74

BeginContext

0.73

 limited

0.72

Activations Density 1.859%

mentions of incorporation and things associated with companies

variations of the word 'limited'

company names

No Comments

No Known Activations