INDEX

Explanations

requests for assistance or communication

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

gas

-0.42

 maximum

-0.41

 bond

-0.41

 Gesch

-0.41

Namara

-0.40

ex

-0.39

型

-0.39

real

-0.38

 proprio

-0.37

 must

-0.37

POSITIVE LOGITS

 оригіналу

1.13

AndEndTag

1.12

ArgsConstructor

1.06

fjspx

0.97

 חיצוניים

0.97

MemoryWarning

0.92

 defaultstate

0.90

Enllaces

0.87

 nahilalakip

0.86

 initComponents

0.85

Activations Density 0.147%

requests for assistance or communication

No Comments

No Known Activations