INDEX

Explanations

a mix of html/mathematical notation and location references

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

-0.48

tis

-0.46

bukkit

-0.44

jfree

-0.44

BASEPATH

-0.44

les

-0.43

la

-0.42

 doGet

-0.42

-0.41

POSITIVE LOGITS

 CreateTagHelper

0.87

 fevere

0.85

Билгалдахарш

0.84

 fidé

0.81

ſelves

0.81

 <=",

0.80

 Reſ

0.80

 étoient

0.79

 Majefty

0.79

 démocr

0.79

Activations Density 0.435%

a mix of html/mathematical notation and location references

No Comments

No Known Activations