INDEX

Explanations

dialogues or conversations with structural indicators such as quotations and turns of speech

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

Personensuche

-0.51

intios

-0.44

shadowOffset

-0.44

mä

-0.42

MessageOf

-0.42

 Wartawan

-0.42

mstyle

-0.41

 heaviest

-0.41

kloped

-0.41

Streamer

-0.40

POSITIVE LOGITS

ersdorf

0.63

 الحره

0.61

 annat

0.60

ymce

0.59

 nahilalakip

0.59

UnusedPrivate

0.58

JspWriter

0.57

 BorderRadius

0.56

 berarti

0.56

مصادر

0.56

Activations Density 0.137%

dialogues or conversations with structural indicators such as quotations and turns of speech

No Comments

No Known Activations