INDEX

Explanations

phrases that indicate an evaluative or comparative statement

oai_token-act-pair · gemini-2.0-flash

danger

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

Portály

-0.59

GEBURTSDATUM

-0.58

Przypisy

-0.58

서는

-0.57

ResumeLayout

-0.56

isContained

-0.49

EndContext

-0.47

 transfieras

-0.46

creativecommons

-0.46

aj

-0.46

POSITIVE LOGITS

 error

1.51

 risk

1.47

error

1.38

risk

1.30

 danger

1.20

 conflict

1.16

Risk

1.15

 threat

1.14

 Risk

1.13

Error

1.12

Activations Density 8.366%

phrases that indicate an evaluative or comparative statement

danger

No Comments

No Known Activations