INDEX

Explanations

negations, understatements, and lack of something

oai_token-act-pair · gemini-2.0-flash

non/under

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

Time

-0.39

In

-0.39

To

-0.38

On

-0.37

Read

-0.37

File

-0.36

Is

-0.34

For

-0.34

It

-0.34

Top

-0.33

POSITIVE LOGITS

FTFY

0.96

enrollment

0.85

enforcement

0.84

arbitrary

0.84

acceptance

0.83

intervention

0.83

preparation

0.82

outcomes

0.82

interference

0.82

explanatory

0.82

Activations Density 44.124%

negations, understatements, and lack of something

non/under

No Comments

No Known Activations