INDEX

Explanations

code snippets with HTML tags and programming terms like Ajax

oai_token-act-pair · gemini-2.0-flash

coding or programming keywords

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

Code snippets

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

tvguidetime

-0.62

 isInitialized

-0.60

 الدولى

-0.60

principalColumn

-0.58

 تانيه

-0.57

 发表于

-0.56

 Offisielt

-0.54

 betweenstory

-0.54

tableFuture

-0.52

BeginContext

-0.52

POSITIVE LOGITS

MigrationBuilder

0.71

 Jahrhundert

0.52

Gambas

0.48

hilfe

0.47

 kjem

0.47

 الرياضيه

0.45

êtes

0.45

Imaginary

0.45

 createSlice

0.44

 utvik

0.44

Activations Density 1.215%

code snippets with HTML tags and programming terms like Ajax

coding or programming keywords

Code snippets

No Comments

No Known Activations