INDEX

Explanations

HTML input and form elements

oai_token-act-pair · gemini-2.0-flash

input

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

input

-0.75

 input

-0.67

 Input

-0.66

Input

-0.66

INPUT

-0.57

Хьажоргаш

-0.55

 INPUT

-0.53

InputModule

-0.52

getInput

-0.50

Inputs

-0.49

POSITIVE LOGITS

CloseOperation

0.65

 smtplib

0.63

 bezeichneter

0.59

 actionPerformed

0.59

 BorderRadius

0.58

 EconPapers

0.56

 poveznice

0.55

 dám

0.54

etcode

0.54

OleDb

0.53

Activations Density 1.044%

HTML input and form elements

input

No Comments

No Known Activations