INDEX

Explanations

sections of code or programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

 ainfi

-0.72

 Paglinawan

-0.71

 indígen

-0.70

 BytesLike

-0.68

UnitTesting

-0.67

iſen

-0.66

 queſta

-0.66

 Verſ

-0.66

 AssemblyCulture

-0.66

RTSC

-0.65

POSITIVE LOGITS

0.53

hline

0.52

0.44

<strong>

0.42

0.41

<blockquote>

0.40

On

0.39

MathML

0.39

0.38

In

0.38

Activations Density 0.056%

sections of code or programming constructs

No Comments

No Known Activations