INDEX

Explanations

what seems to be proper nouns, code and fragments of internet addresses

oai_token-act-pair · gemini-2.0-flash

random text snippets

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

poda

-0.45

en

-0.44

clus

-0.41

 perish

-0.41

bal

-0.41

Ved

-0.38

中

-0.38

在

-0.37

vidad

-0.37

dato

-0.37

POSITIVE LOGITS

WithIOException

0.94

ThroughAttribute

0.92

 CreateTagHelper

0.88

SourceChecksum

0.85

 nahilalakip

0.83

styleType

0.80

#+#

0.77

 gynhyrchwyd

0.75

 transfieras

0.72

jsonwebtoken

0.71

Activations Density 0.365%

what seems to be proper nouns, code and fragments of internet addresses

random text snippets

No Comments

No Known Activations