INDEX

Explanations

terms related to classification and categorization

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

comparisons or classifications being made between different groups or categories.

oai_token-act-pair · claude-4-5-haiku Triggered by @emiglarou

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.31.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

SequentialGroup

-0.55

发表于

-0.55

IntoConstraints

-0.50

BeginInit

-0.48

SharedCtor

-0.44

RenderAtEndOf

-0.44

<?

-0.44

 defaultstate

-0.44

MENAFN

-0.43

 برانيه

-0.42

POSITIVE LOGITS

 based

2.95

 Based

2.44

 BASED

2.34

Based

2.34

based

2.27

 berdasarkan

2.20

 basado

2.05

 dựa

2.02

 basierend

1.98

 baseado

1.94

Activations Density 2.176%

terms related to classification and categorization

comparisons or classifications being made between different groups or categories.

No Comments

No Known Activations