INDEX

Explanations

alpha-numeric sequences that might be sensor IDs or figure references

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

 armp

-0.46

lock

-0.45

rath

-0.45

Verdana

-0.44

 الحره

-0.44

leistungs

-0.44

 Einige

-0.44

입

-0.42

諱

-0.41

Lock

-0.41

POSITIVE LOGITS

<bos>

0.84

 Waray

0.78

#+#

0.77

 BorderRadius

0.77

)++;

0.73

DockStyle

0.73

ⓧ

0.71

 surla

0.69

KommentareTeilen

0.68

 referenties

0.68

Activations Density 1.998%

alpha-numeric sequences that might be sensor IDs or figure references

No Comments

No Known Activations