INDEX

Explanations

the word "temporary" and words related to magnets

oai_token-act-pair · gemini-2.0-flash

temporary/permanent

np_max-act · gemini-2.0-flash

temporary vs permanent

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

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 itſelf

-2.72

Efq

-2.67

 myſelf

-2.58

 Monfieur

-2.38

 Majefty

-2.34

 Jefus

-2.34

 Houſe

-2.30

 Theſe

-2.25

 Reſ

-2.23

 pleaſure

-2.23

POSITIVE LOGITS

1.41

1.12

1.10

...

1.09

1.06

<eos>

1.04

1.03

0.98

Activations Density 1.393%

the word "temporary" and words related to magnets

temporary/permanent

temporary vs permanent

No Comments

No Known Activations