INDEX

Explanations

titles and honorifics used to address individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

 between

-0.49

JScrollPane

-0.47

QSize

-0.46

-0.44

ndre

-0.44

IBAction

-0.42

openzeppelin

-0.41

ConverterFactory

-0.41

AxisAlignment

-0.40

Between

-0.40

POSITIVE LOGITS

 tartalomajánló

0.82

 препратки

0.77

 صوتيه

0.72

 dearest

0.71

 <>",

0.70

الدراسه

0.68

moiselle

0.67

 Bioaccumulative

0.67

Архівовано

0.64

̍t

0.64

Activations Density 0.164%

titles and honorifics used to address individuals

No Comments

No Known Activations