INDEX

Explanations

words and phrases that refer to rules and regulations

oai_token-act-pair · gemini-2.0-flash

permissions related to alcohol

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

allow

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

 pleaſure

-0.94

 &___

-0.92

 purpoſe

-0.88

 raiſ

-0.84

 myſelf

-0.82

 uſe

-0.82

 Jefus

-0.82

 kasarigan

-0.79

 poffible

-0.79

 ſtate

-0.79

POSITIVE LOGITS

 Allow

2.22

 allow

2.22

Allow

2.17

allow

2.08

 allowed

2.08

 allowing

2.00

 ALLOW

1.93

 Allowing

1.93

 allows

1.92

 permitting

1.83

Activations Density 5.237%

words and phrases that refer to rules and regulations

permissions related to alcohol

allow

No Comments

No Known Activations