INDEX

Explanations

content related to medicine and health care

oai_token-act-pair · gemini-2.0-flash

technical terms and concepts

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

content enhancement

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

:+:

-0.60

didSet

-0.59

IInterface

-0.56

Naissance

-0.55

ฤษ

-0.54

 مشين

-0.53

setScene

-0.52

INTS

-0.50

 ListTile

-0.49

ubility

-0.48

POSITIVE LOGITS

+)/

0.52

Portale

0.52

 Мексичка

0.50

égalité

0.49

 gerek

0.49

 skin

0.49

AddTagHelper

0.49

CodeDom

0.49

Govern

0.48

 motivadoras

0.47

Activations Density 1.584%

content related to medicine and health care

technical terms and concepts

content enhancement

No Comments

No Known Activations