INDEX

Explanations

HTML tags and CSS class names

oai_token-act-pair · gemini-2.0-flash

tokens related to HTML and CSS structure

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

=

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

MENAFN

-0.47

 nakalista

-0.43

<bos>

-0.40

 createState

-0.37

numbers

-0.37

LEIA

-0.36

tra

-0.35

IEDAD

-0.35

SystemColors

-0.35

 NgModule

-0.35

POSITIVE LOGITS

 typelib

0.88

دانشنامهٔ

0.84

DockStyle

0.77

 kasarigan

0.71

 CreateTagHelper

0.69

RuleContext

0.68

ImageContext

0.67

 للاسماء

0.67

 raiſ

0.66

 betweenstory

0.66

Activations Density 0.305%

HTML tags and CSS class names

tokens related to HTML and CSS structure

=

No Comments

No Known Activations