INDEX

Explanations

instances of personal reflections or thoughts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

います

-0.67

ufficio

-0.56

 zufolge

-0.56

 Fenn

-0.55

 pungkas

-0.53

 čierna

-0.53

 capacités

-0.53

 DIOS

-0.52

 Myster

-0.51

 disciplines

-0.51

POSITIVE LOGITS

Personendaten

0.83

verwijspagina

0.81

 Thought

0.76

thought

0.76

 nahilalakip

0.74

 Wikimedijinoj

0.73

 THOUGHT

0.72

OGND

0.72

WithIOException

0.71

 hoped

0.71

Activations Density 0.131%

instances of personal reflections or thoughts

No Comments

No Known Activations