INDEX

Explanations

code snippets using bracket syntax and a specific set of keywords like item, restaurant, or style

oai_token-act-pair · gemini-2.0-flash

archaic or unusual spellings

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

-0.88

'])){

-0.79

ELINES

-0.75

et

-0.74

ulaski

-0.74

VELOP

-0.73

di

-0.73

POSITIVE LOGITS

 itſelf

1.24

 pleaſure

1.17

 Reſ

1.14

 myſelf

1.14

 greateſt

1.12

 fubject

1.10

 Monfieur

1.10

 reaſon

1.10

 poffe

1.09

 Majefty

1.07

Activations Density 5.537%

code snippets using bracket syntax and a specific set of keywords like item, restaurant, or style

archaic or unusual spellings

Code snippets

No Comments

No Known Activations