INDEX

Explanations

programming language components and syntax

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

 ModelExpression

-0.56

MessageOf

-0.53

 betweenstory

-0.51

wiſe

-0.50

 Италијани

-0.50

 ſta

-0.49

 queſta

-0.48

 سكانية

-0.48

ſelf

-0.47

 faſt

-0.47

POSITIVE LOGITS

::{

0.96

::

0.75

CppMethod

0.62

::*;

0.54

::~

0.48

 sepol

0.44

BeginInit

0.43

#![

0.42

CloseOperation

0.40

Activations Density 0.001%

programming language components and syntax

No Comments

No Known Activations