INDEX

Explanations

words related to situations, feelings, or events, especially those that are challenging or important.

oai_token-act-pair · gemini-2.0-flash

stories and narratives

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

opoulos

-0.45

 practical

-0.45

下一

-0.42

 involved

-0.42

ObjectMeta

-0.41

yttää

-0.40

routeProvider

-0.40

vok

-0.39

Embeddable

-0.39

 Osten

-0.39

POSITIVE LOGITS

 worth

1.13

 WORTH

0.99

 Worth

0.91

SourceChecksum

0.85

WORTH

0.79

Worth

0.77

帖最后由

0.77

worth

0.72

 صوتيه

0.71

发表于

0.68

Activations Density 1.459%

words related to situations, feelings, or events, especially those that are challenging or important.

stories and narratives

No Comments

No Known Activations