INDEX

Explanations

references to society and its structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

AutoresizingMask

-0.45

TRAILING

-0.41

 anchor

-0.37

XmlAttribute

-0.36

 Alan

-0.36

Uns

-0.36

 dirty

-0.36

 Aston

-0.35

Alan

-0.35

REM

-0.35

POSITIVE LOGITS

 society

3.94

 Society

3.89

Society

3.83

 SOCIETY

3.66

society

3.64

 societies

3.00

 Societies

2.78

 sociedad

2.69

 sociedade

2.63

 общества

2.39

Activations Density 0.100%

references to society and its structure

No Comments

No Known Activations