INDEX

Explanations

code snippets with the word "output"

oai_token-act-pair · gemini-2.0-flash

output

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

IFrame

Link

Negative Logits

 output

-1.27

 outputs

-1.13

output

-1.13

 Output

-1.09

Output

-1.09

 OUTPUT

-0.97

 Outputs

-0.94

输出

-0.93

getOutput

-0.89

 输出

-0.87

POSITIVE LOGITS

MetaObject

0.52

 tiên

0.47

:]:

0.47

NewUrlParser

0.46

ísimo

0.45

StreetMap

0.44

anzen

0.44

ValueStyle

0.43

 HttpHeaders

0.41

 المتحدة

0.41

Activations Density 13.784%

code snippets with the word "output"

output

No Known Activations

code snippets with the word "output"

output

No Known Activations