INDEX

Explanations

strings of text with '$' in them, followed by 'Nr.'

oai_token-act-pair · gemini-2.0-flash

tokens with special characters or formatting

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

Code/programming related text

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Monfieur

-1.74

 myſelf

-1.64

Efq

-1.64

 whoſe

-1.61

 ſeveral

-1.60

 itſelf

-1.58

 Theſe

-1.55

 Reſ

-1.52

 Diſ

-1.52

 Jefus

-1.49

POSITIVE LOGITS

de

0.53

0.50

0.49

0.48

0.47

0.46

0.45

Activations Density 0.852%

strings of text with '$' in them, followed by 'Nr.'

tokens with special characters or formatting

Code/programming related text

No Comments

No Known Activations