INDEX

Explanations

SQL commands

oai_token-act-pair · gemini-2.0-flash

SQL command keywords

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

SQL commands

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

mtd

-0.51

je

-0.49

lagen

-0.49

yn

-0.48

cal

-0.47

for

-0.46

dy

-0.43

dl

-0.43

ness

-0.43

<eos>

-0.43

POSITIVE LOGITS

StoryboardSegue

0.97

 initComponents

0.95

MigrationBuilder

0.91

WriteBarrier

0.89

 विश्वसनीयता

0.89

stdc

0.85

 ویکی‌پدیای

0.85

RetentionPolicy

0.83

 Normdatei

0.82

TagMode

0.82

Activations Density 0.728%

SQL commands

SQL command keywords

SQL commands

No Comments

No Known Activations