INDEX

Explanations

words related to questions and answers

oai_token-act-pair · gemini-2.0-flash

questions and problems

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Questions

-0.79

 Issues

-0.76

 questions

-0.75

 Questions

-0.74

problems

-0.73

questions

-0.73

Issues

-0.73

 issues

-0.71

issues

-0.71

 problems

-0.70

POSITIVE LOGITS

aarrggbb

0.70

 HasFactory

0.66

PerformLayout

0.66

SharedDtor

0.60

 חיצוניים

0.60

principalColumn

0.59

glGen

0.58

__.__

0.57

 Paglinawan

0.56

 Biôgrafia

0.54

Activations Density 5.968%

words related to questions and answers

questions and problems

No Comments

No Known Activations