INDEX

Explanations

the letter 'e' followed by a hyphen or another letter

oai_token-act-pair · gemini-2.0-flash

technical/code related

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

-0.66

-0.58

-0.54

vare

-0.54

-0.49

De

-0.49

On

-0.48

POSITIVE LOGITS

 Monfieur

0.90

 Administrativna

0.83

 Diſ

0.82

 MainAxisSize

0.82

 greateſt

0.79

 ſeveral

0.78

 GenerationType

0.77

WriteBarrier

0.75

 pleaſure

0.75

 Houſe

0.74

Activations Density 2.050%

the letter 'e' followed by a hyphen or another letter

technical/code related

No Comments

No Known Activations