INDEX

Explanations

code snippets, especially related to python and including commands, scripts, and processes

oai_token-act-pair · gemini-2.0-flash

programming, command lines

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

-0.51

|}

-0.43

↵↵

-0.40

-0.39

 gyakor

-0.39

//

-0.39

ApiModel

-0.38

忙

-0.38

osoba

-0.38

•

-0.36

POSITIVE LOGITS

optarg

0.88

OrBuilder

0.81

 argc

0.76

 argparse

0.74

0.70

."</

0.69

__':

0.67

 MessageBoxIcon

0.66

 BrowserModule

0.66

xiety

0.65

Activations Density 0.514%

code snippets, especially related to python and including commands, scripts, and processes

programming, command lines

No Comments

No Known Activations