INDEX

Explanations

URLs and web links

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

URLs

oai_token-act-pair · gemini-2.0-flash

://

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

-0.62

-0.57

-0.56

-0.55

ten

-0.54

IV

-0.54

 base

-0.52

POSITIVE LOGITS

 Majefty

0.99

 greateſt

0.90

 pleaſure

0.90

 itſelf

0.89

 myſelf

0.89

 Diſ

0.88

 ſtate

0.88

 preſent

0.86

 Chriftian

0.85

 Anſ

0.84

Activations Density 1.052%

URLs and web links

URLs

://

No Comments

No Known Activations