INDEX

Explanations

HTML attributes or elements related to styling or scripting, often involving the terms "class", "id", or "value"

oai_token-act-pair · gemini-2.0-flash

HTML attributes

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

id

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

-0.68

-0.56

-0.54

-0.49

<eos>

-0.48

mo

-0.48

-0.47

urio

-0.47

POSITIVE LOGITS

énario

0.91

ftagPool

0.82

 itſelf

0.81

Efq

0.79

 ―――――

0.78

 myſelf

0.77

 raiſ

0.76

ſelves

0.74

LookAnd

0.72

 Савезне

0.69

Activations Density 0.247%

HTML attributes or elements related to styling or scripting, often involving the terms "class", "id", or "value"

HTML attributes

id

No Comments

No Known Activations