INDEX

Explanations

words relating to neural networks, classification, secret information, and parties

oai_token-act-pair · gemini-2.0-flash

hidden/secret

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

 secret

-2.20

secret

-1.91

 Secret

-1.91

 hidden

-1.89

Secret

-1.84

hidden

-1.71

Hidden

-1.63

 SECRET

-1.57

 Hidden

-1.57

 secreto

-1.47

POSITIVE LOGITS

 चीज़ों

0.98

InvalidProtocol

0.95

DebuggerNonUser

0.83

 Theſe

0.81

例句

0.79

 Shakspeare

0.77

WriteBarrier

0.77

principalTable

0.74

 الرياضيه

0.73

+#+#

0.72

Activations Density 10.205%

words relating to neural networks, classification, secret information, and parties

hidden/secret

No Comments

No Known Activations