INDEX

Explanations

a space followed by a number

oai_token-act-pair · gemini-2.0-flash

programming-related terms

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

▁

np_max-act-logits · gpt-5-mini Triggered by @chenshw0109

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

ss

-0.48

-0.46

bes

-0.45

<eos>

-0.43

ro

-0.41

WriteString

-0.41

id

-0.40

str

-0.39

it

-0.39

lis

-0.38

POSITIVE LOGITS

 snippetHide

0.99

CloseOperation

0.98

extAlignment

0.93

 FetchType

0.92

 MainAxisSize

0.91

thâu

0.90

/**

0.90

 للمعارف

0.89

✨:

0.87

 GenerationType

0.85

Activations Density 1.539%

a space followed by a number

programming-related terms

▁

No Comments

No Known Activations