INDEX

Explanations

the string "spec" followed by different suffixes

oai_token-act-pair · gemini-2.0-flash

the word 'spec'

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

spec

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

 BoxFit

-0.81

AndEndTag

-0.76

 Waray

-0.73

CppCodeGen

-0.71

 تانيه

-0.68

 AssemblyTitle

-0.66

 defaultstate

-0.65

GraphicsUnit

-0.65

 مواليد

-0.64

uxxxx

-0.63

POSITIVE LOGITS

 betweenstory

0.60

 rechten

0.40

toByteArray

0.39

ess

0.39

saver

0.38

นำ

0.38

getInputStream

0.38

liceerd

0.37

Saver

0.37

walks

0.37

Activations Density 0.687%

the string "spec" followed by different suffixes

the word 'spec'

spec

No Comments

No Known Activations