INDEX

Explanations

code snippets, especially those related to databases and queries

oai_token-act-pair · gemini-2.0-flash

words or patterns in programming context

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

code

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

StructEnd

-0.81

 تضيفلها

-0.73

URLException

-0.70

:]:

-0.67

 transfieras

-0.66

曖昧さ回避

-0.65

 defaultstate

-0.65

 transférez

-0.64

 Савезне

-0.63

 CreateTagHelper

-0.61

POSITIVE LOGITS

oo

0.55

 Qaraldi

0.50

pro

0.46

ly

0.46

جو

0.46

ooo

0.45

jini

0.44

At

0.43

ెక్

0.43

 Ciências

0.43

Activations Density 5.225%

code snippets, especially those related to databases and queries

words or patterns in programming context

code

No Comments

No Known Activations